wehub/ymcui--chinese-llama-alpaca
1
0
Fork 0
Code Issues Pull Requests Actions Deployments Packages Projects Releases Wiki Activity
Files
ffb1cdfcf7aee66cfb9bde1e418e8ffc251af837
ymcui--chinese-llama-alpaca/notebooks/convert_and_quantize_chinese_llama_and_alpaca.ipynb
T
wehub-resource-sync ffb1cdfcf7 chore: import upstream snapshot with attribution
2026-07-13 13:27:00 +08:00

2568 lines
244 KiB
Plaintext
Vendored
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"provenance": [],
"machine_shape": "hm",
"gpuType": "T4"
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
},
"language_info": {
"name": "python"
}
},
"cells": [
{
"cell_type": "markdown",
"source": [
"# 转换并量化中文LLaMA和Alpaca模型\n",
"\n",
"项目地址：https://github.com/ymcui/Chinese-LLaMA-Alpaca\n",
"\n",
"⚠️ 内存消耗提示（确保刷出来的机器RAM大于以下要求）：\n",
"- 7B模型：15G+\n",
"- 13B模型：18G+\n",
"- 33B模型：22G+\n",
"\n",
"💡 提示和小窍门：\n",
"- 免费用户默认的内存只有12G左右，不足以转换模型。**实测选择TPU的话有机会随机出35G内存**，建议多试几次\n",
"- Pro(+)用户请选择 “代码执行程序” -> “更改运行时类型” -> “高RAM”\n",
"- 程序莫名崩掉或断开连接就说明内存爆了\n",
"- 如果选了“高RAM”之后内存还是不够大的话，选择以下操作，有的时候会分配出很高内存的机器，祝你好运😄！\n",
" - 可以把GPU或者TPU也选上（虽然不会用到）\n",
" - 选GPU时，Pro(+)用户可选“A100”类型GPU\n",
"\n",
"*温馨提示：用完之后注意断开运行时，选择满足要求的最低配置即可，避免不必要的计算单元消耗（Pro只给100个计算单元）。*"
],
"metadata": {
"id": "B1c96_k3MahN"
}
},
{
"cell_type": "markdown",
"source": [
"## 安装相关依赖"
],
"metadata": {
"id": "vScqHD_jMFOV"
}
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "E5WKFJXIL6ZU",
"outputId": "a7baeebb-9b74-4d14-93dc-fb1f6e1b3716"
},
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n",
"Requirement already satisfied: torch==1.13.1 in /usr/local/lib/python3.10/dist-packages (1.13.1)\n",
"Requirement already satisfied: typing-extensions in /usr/local/lib/python3.10/dist-packages (from torch==1.13.1) (4.5.0)\n",
"Requirement already satisfied: nvidia-cuda-runtime-cu11==11.7.99 in /usr/local/lib/python3.10/dist-packages (from torch==1.13.1) (11.7.99)\n",
"Requirement already satisfied: nvidia-cudnn-cu11==8.5.0.96 in /usr/local/lib/python3.10/dist-packages (from torch==1.13.1) (8.5.0.96)\n",
"Requirement already satisfied: nvidia-cublas-cu11==11.10.3.66 in /usr/local/lib/python3.10/dist-packages (from torch==1.13.1) (11.10.3.66)\n",
"Requirement already satisfied: nvidia-cuda-nvrtc-cu11==11.7.99 in /usr/local/lib/python3.10/dist-packages (from torch==1.13.1) (11.7.99)\n",
"Requirement already satisfied: setuptools in /usr/local/lib/python3.10/dist-packages (from nvidia-cublas-cu11==11.10.3.66->torch==1.13.1) (67.7.2)\n",
"Requirement already satisfied: wheel in /usr/local/lib/python3.10/dist-packages (from nvidia-cublas-cu11==11.10.3.66->torch==1.13.1) (0.40.0)\n",
"Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n",
"Requirement already satisfied: transformers==4.30.2 in /usr/local/lib/python3.10/dist-packages (4.30.2)\n",
"Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from transformers==4.30.2) (3.12.0)\n",
"Requirement already satisfied: huggingface-hub<1.0,>=0.14.1 in /usr/local/lib/python3.10/dist-packages (from transformers==4.30.2) (0.15.1)\n",
"Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.10/dist-packages (from transformers==4.30.2) (1.22.4)\n",
"Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from transformers==4.30.2) (23.1)\n",
"Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from transformers==4.30.2) (6.0)\n",
"Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.10/dist-packages (from transformers==4.30.2) (2022.10.31)\n",
"Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from transformers==4.30.2) (2.27.1)\n",
"Requirement already satisfied: tokenizers!=0.11.3,<0.14,>=0.11.1 in /usr/local/lib/python3.10/dist-packages (from transformers==4.30.2) (0.13.3)\n",
"Requirement already satisfied: safetensors>=0.3.1 in /usr/local/lib/python3.10/dist-packages (from transformers==4.30.2) (0.3.1)\n",
"Requirement already satisfied: tqdm>=4.27 in /usr/local/lib/python3.10/dist-packages (from transformers==4.30.2) (4.65.0)\n",
"Requirement already satisfied: fsspec in /usr/local/lib/python3.10/dist-packages (from huggingface-hub<1.0,>=0.14.1->transformers==4.30.2) (2023.4.0)\n",
"Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub<1.0,>=0.14.1->transformers==4.30.2) (4.5.0)\n",
"Requirement already satisfied: urllib3<1.27,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->transformers==4.30.2) (1.26.15)\n",
"Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->transformers==4.30.2) (2022.12.7)\n",
"Requirement already satisfied: charset-normalizer~=2.0.0 in /usr/local/lib/python3.10/dist-packages (from requests->transformers==4.30.2) (2.0.12)\n",
"Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->transformers==4.30.2) (3.4)\n",
"Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n",
"Collecting peft==0.3.0\n",
" Downloading peft-0.3.0-py3-none-any.whl (56 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m56.8/56.8 kB\u001b[0m \u001b[31m2.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.10/dist-packages (from peft==0.3.0) (1.22.4)\n",
"Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from peft==0.3.0) (23.1)\n",
"Requirement already satisfied: psutil in /usr/local/lib/python3.10/dist-packages (from peft==0.3.0) (5.9.5)\n",
"Requirement already satisfied: pyyaml in /usr/local/lib/python3.10/dist-packages (from peft==0.3.0) (6.0)\n",
"Requirement already satisfied: torch>=1.13.0 in /usr/local/lib/python3.10/dist-packages (from peft==0.3.0) (1.13.1)\n",
"Requirement already satisfied: transformers in /usr/local/lib/python3.10/dist-packages (from peft==0.3.0) (4.30.2)\n",
"Collecting accelerate (from peft==0.3.0)\n",
" Downloading accelerate-0.20.3-py3-none-any.whl (227 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m227.6/227.6 kB\u001b[0m \u001b[31m10.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: typing-extensions in /usr/local/lib/python3.10/dist-packages (from torch>=1.13.0->peft==0.3.0) (4.5.0)\n",
"Requirement already satisfied: nvidia-cuda-runtime-cu11==11.7.99 in /usr/local/lib/python3.10/dist-packages (from torch>=1.13.0->peft==0.3.0) (11.7.99)\n",
"Requirement already satisfied: nvidia-cudnn-cu11==8.5.0.96 in /usr/local/lib/python3.10/dist-packages (from torch>=1.13.0->peft==0.3.0) (8.5.0.96)\n",
"Requirement already satisfied: nvidia-cublas-cu11==11.10.3.66 in /usr/local/lib/python3.10/dist-packages (from torch>=1.13.0->peft==0.3.0) (11.10.3.66)\n",
"Requirement already satisfied: nvidia-cuda-nvrtc-cu11==11.7.99 in /usr/local/lib/python3.10/dist-packages (from torch>=1.13.0->peft==0.3.0) (11.7.99)\n",
"Requirement already satisfied: setuptools in /usr/local/lib/python3.10/dist-packages (from nvidia-cublas-cu11==11.10.3.66->torch>=1.13.0->peft==0.3.0) (67.7.2)\n",
"Requirement already satisfied: wheel in /usr/local/lib/python3.10/dist-packages (from nvidia-cublas-cu11==11.10.3.66->torch>=1.13.0->peft==0.3.0) (0.40.0)\n",
"Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from transformers->peft==0.3.0) (3.12.0)\n",
"Requirement already satisfied: huggingface-hub<1.0,>=0.14.1 in /usr/local/lib/python3.10/dist-packages (from transformers->peft==0.3.0) (0.15.1)\n",
"Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.10/dist-packages (from transformers->peft==0.3.0) (2022.10.31)\n",
"Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from transformers->peft==0.3.0) (2.27.1)\n",
"Requirement already satisfied: tokenizers!=0.11.3,<0.14,>=0.11.1 in /usr/local/lib/python3.10/dist-packages (from transformers->peft==0.3.0) (0.13.3)\n",
"Requirement already satisfied: safetensors>=0.3.1 in /usr/local/lib/python3.10/dist-packages (from transformers->peft==0.3.0) (0.3.1)\n",
"Requirement already satisfied: tqdm>=4.27 in /usr/local/lib/python3.10/dist-packages (from transformers->peft==0.3.0) (4.65.0)\n",
"Requirement already satisfied: fsspec in /usr/local/lib/python3.10/dist-packages (from huggingface-hub<1.0,>=0.14.1->transformers->peft==0.3.0) (2023.4.0)\n",
"Requirement already satisfied: urllib3<1.27,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->transformers->peft==0.3.0) (1.26.15)\n",
"Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->transformers->peft==0.3.0) (2022.12.7)\n",
"Requirement already satisfied: charset-normalizer~=2.0.0 in /usr/local/lib/python3.10/dist-packages (from requests->transformers->peft==0.3.0) (2.0.12)\n",
"Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->transformers->peft==0.3.0) (3.4)\n",
"Installing collected packages: accelerate, peft\n",
"Successfully installed accelerate-0.20.3 peft-0.3.0\n",
"Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n",
"Requirement already satisfied: sentencepiece in /usr/local/lib/python3.10/dist-packages (0.1.99)\n"
]
}
],
"source": [
"!pip install torch==1.13.1\n",
"!pip install transformers==4.30.2\n",
"!pip install peft==0.3.0\n",
"!pip install sentencepiece"
]
},
{
"cell_type": "markdown",
"source": [
"## 克隆目录和代码"
],
"metadata": {
"id": "ygb1xFIMNQKw"
}
},
{
"cell_type": "code",
"source": [
"!git clone https://github.com/ymcui/Chinese-LLaMA-Alpaca\n",
"!git clone https://github.com/ggerganov/llama.cpp"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "yCEJh7NJNXz9",
"outputId": "bfa34a83-a8b9-4e24-e956-83c7313eb448"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Cloning into 'Chinese-LLaMA-Alpaca'...\n",
"remote: Enumerating objects: 1407, done.\u001b[K\n",
"remote: Counting objects: 100% (599/599), done.\u001b[K\n",
"remote: Compressing objects: 100% (257/257), done.\u001b[K\n",
"remote: Total 1407 (delta 369), reused 494 (delta 338), pack-reused 808\u001b[K\n",
"Receiving objects: 100% (1407/1407), 22.61 MiB | 27.14 MiB/s, done.\n",
"Resolving deltas: 100% (831/831), done.\n",
"Cloning into 'llama.cpp'...\n",
"remote: Enumerating objects: 3618, done.\u001b[K\n",
"remote: Counting objects: 100% (1155/1155), done.\u001b[K\n",
"remote: Compressing objects: 100% (124/124), done.\u001b[K\n",
"remote: Total 3618 (delta 1076), reused 1036 (delta 1031), pack-reused 2463\u001b[K\n",
"Receiving objects: 100% (3618/3618), 3.28 MiB | 21.36 MiB/s, done.\n",
"Resolving deltas: 100% (2424/2424), done.\n"
]
}
]
},
{
"cell_type": "markdown",
"source": [
"## 合并模型（以Alpaca-7B为例）\n",
"\n",
"此处使用的是🤗模型库中提供的基模型（已是HF格式），而不是Facebook官方的LLaMA模型，因此略去将原版LLaMA转换为HF格式的步骤。\n",
"**这里直接运行第二步：合并LoRA权重**，生成全量模型权重。可以直接指定🤗模型库的地址，也可以是本地存放地址。\n",
"- 基模型：`elinas/llama-7b-hf-transformers-4.29` *（use at your own risk，我们比对过SHA256和正版一致，但你应确保自己有权使用该模型）*\n",
"- LoRA模型：`ziqingyang/chinese-alpaca-lora-7b`\n",
" - 如果是Alpaca-Plus模型，记得要同时传入llama和alpaca的lora，教程：[这里](https://github.com/ymcui/Chinese-LLaMA-Alpaca/wiki/手动模型合并与转换#多lora权重合并适用于chinese-alpaca-plus)\n",
"- 输出格式：可选pth或者huggingface，这里选择pth，因为后面要用llama.cpp量化\n",
"\n",
"由于要下载模型，所以需要耐心等待一下，尤其是33B模型。\n",
"转换好的模型存放在`alpaca-combined`目录。\n",
"如果你不需要量化模型，那么到这一步就结束了，可自行下载或者转存到Google Drive。"
],
"metadata": {
"id": "nIyxX0DSNsgQ"
}
},
{
"cell_type": "code",
"source": [
"!python ./Chinese-LLaMA-Alpaca/scripts/merge_llama_with_chinese_lora_low_mem.py \\\n",
" --base_model 'elinas/llama-7b-hf-transformers-4.29' \\\n",
" --lora_model 'ziqingyang/chinese-alpaca-lora-7b' \\\n",
" --output_type pth \\\n",
" --output_dir alpaca-combined"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "5AV4EW5hNhVV",
"outputId": "5cb36099-4ca1-403e-c6b5-c8c8441eaa11"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Base model: elinas/llama-7b-hf-transformers-4.29\n",
"LoRA model(s) ['ziqingyang/chinese-alpaca-lora-7b']:\n",
"Loading ziqingyang/chinese-alpaca-lora-7b\n",
"Cannot find lora model on the disk. Downloading lora model from hub...\n",
"Fetching 7 files: 0% 0/7 [00:00<?, ?it/s]\n",
"Downloading (…)c39d6ac454/README.md: 100% 316/316 [00:00<00:00, 1.93MB/s]\n",
"\n",
"Downloading (…)/adapter_config.json: 100% 472/472 [00:00<00:00, 3.48MB/s]\n",
"\n",
"Downloading (…)cial_tokens_map.json: 100% 96.0/96.0 [00:00<00:00, 661kB/s]\n",
"\n",
"Downloading (…)ac454/.gitattributes: 100% 1.48k/1.48k [00:00<00:00, 7.92MB/s]\n",
"Fetching 7 files: 14% 1/7 [00:00<00:00, 6.42it/s]\n",
"Downloading (…)okenizer_config.json: 100% 166/166 [00:00<00:00, 804kB/s]\n",
"\n",
"Downloading tokenizer.model: 0% 0.00/758k [00:00<?, ?B/s]\u001b[A\n",
"\n",
"Downloading tokenizer.model: 100% 758k/758k [00:00<00:00, 15.6MB/s]\n",
"\n",
"\n",
"Downloading adapter_model.bin: 1% 10.5M/858M [00:00<00:12, 66.0MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 2% 21.0M/858M [00:00<00:11, 75.2MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 4% 31.5M/858M [00:00<00:10, 78.9MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 5% 41.9M/858M [00:00<00:10, 80.0MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 6% 52.4M/858M [00:00<00:10, 78.9MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 7% 62.9M/858M [00:00<00:10, 77.5MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 9% 73.4M/858M [00:00<00:09, 80.0MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 10% 83.9M/858M [00:01<00:09, 78.4MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 11% 94.4M/858M [00:01<00:09, 80.8MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 12% 105M/858M [00:01<00:09, 82.9MB/s] \u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 13% 115M/858M [00:01<00:08, 82.9MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 15% 126M/858M [00:01<00:08, 84.1MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 16% 136M/858M [00:01<00:09, 78.2MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 17% 147M/858M [00:01<00:09, 78.4MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 18% 157M/858M [00:01<00:08, 80.5MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 20% 168M/858M [00:02<00:08, 78.1MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 21% 178M/858M [00:02<00:08, 81.4MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 22% 189M/858M [00:02<00:08, 78.1MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 23% 199M/858M [00:02<00:08, 78.7MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 24% 210M/858M [00:02<00:07, 81.3MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 26% 220M/858M [00:02<00:07, 81.2MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 27% 231M/858M [00:02<00:07, 82.5MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 28% 241M/858M [00:03<00:07, 82.3MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 29% 252M/858M [00:03<00:07, 83.6MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 31% 262M/858M [00:03<00:07, 80.5MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 32% 273M/858M [00:03<00:07, 82.3MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 33% 283M/858M [00:03<00:06, 82.3MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 34% 294M/858M [00:03<00:06, 84.2MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 35% 304M/858M [00:03<00:06, 82.5MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 37% 315M/858M [00:03<00:06, 79.9MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 38% 325M/858M [00:04<00:06, 82.7MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 39% 336M/858M [00:04<00:06, 84.1MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 40% 346M/858M [00:04<00:05, 85.6MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 42% 357M/858M [00:04<00:05, 86.9MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 43% 367M/858M [00:04<00:05, 87.8MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 44% 377M/858M [00:04<00:05, 87.3MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 45% 388M/858M [00:04<00:05, 88.2MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 46% 398M/858M [00:04<00:05, 85.8MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 48% 409M/858M [00:04<00:05, 85.2MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 49% 419M/858M [00:05<00:05, 85.7MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 50% 430M/858M [00:05<00:05, 84.5MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 51% 440M/858M [00:05<00:04, 85.6MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 53% 451M/858M [00:05<00:04, 86.3MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 54% 461M/858M [00:05<00:04, 87.6MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 55% 472M/858M [00:05<00:04, 87.5MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 56% 482M/858M [00:05<00:04, 85.3MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 57% 493M/858M [00:05<00:04, 84.6MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 59% 503M/858M [00:06<00:04, 85.3MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 60% 514M/858M [00:06<00:04, 85.1MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 61% 524M/858M [00:06<00:03, 85.6MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 62% 535M/858M [00:06<00:03, 86.7MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 64% 545M/858M [00:06<00:03, 87.5MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 65% 556M/858M [00:06<00:03, 89.2MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 66% 566M/858M [00:06<00:03, 89.6MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 67% 577M/858M [00:06<00:03, 89.6MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 68% 587M/858M [00:07<00:03, 85.8MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 70% 598M/858M [00:07<00:03, 86.4MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 71% 608M/858M [00:07<00:02, 88.2MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 72% 619M/858M [00:07<00:02, 89.0MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 73% 629M/858M [00:07<00:02, 85.7MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 75% 640M/858M [00:07<00:02, 81.9MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 76% 650M/858M [00:07<00:02, 80.6MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 77% 661M/858M [00:07<00:02, 81.7MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 78% 671M/858M [00:08<00:02, 82.8MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 79% 682M/858M [00:08<00:02, 76.3MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 81% 692M/858M [00:08<00:02, 79.8MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 82% 703M/858M [00:08<00:01, 80.9MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 83% 713M/858M [00:08<00:01, 80.5MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 84% 724M/858M [00:08<00:01, 83.1MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 85% 734M/858M [00:08<00:01, 85.2MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 87% 744M/858M [00:08<00:01, 84.9MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 88% 755M/858M [00:09<00:01, 83.9MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 89% 765M/858M [00:09<00:01, 81.9MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 90% 776M/858M [00:09<00:00, 85.2MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 92% 786M/858M [00:09<00:00, 86.6MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 93% 797M/858M [00:09<00:00, 85.9MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 94% 807M/858M [00:09<00:00, 87.7MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 95% 818M/858M [00:09<00:00, 86.0MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 96% 828M/858M [00:09<00:00, 87.4MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 98% 839M/858M [00:10<00:00, 86.8MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 99% 849M/858M [00:10<00:00, 82.4MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading adapter_model.bin: 100% 858M/858M [00:10<00:00, 83.3MB/s]\n",
"Fetching 7 files: 100% 7/7 [00:10<00:00, 1.50s/it]\n",
"Cannot find lora model on the disk. Downloading lora model from hub...\n",
"Fetching 11 files: 0% 0/11 [00:00<?, ?it/s]\n",
"Downloading (…)a55fdb7a/config.json: 100% 507/507 [00:00<00:00, 2.66MB/s]\n",
"\n",
"Downloading (…)l-00001-of-00002.bin: 0% 0.00/9.98G [00:00<?, ?B/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 0% 0.00/3.50G [00:00<?, ?B/s]\u001b[A\u001b[A\n",
"\n",
"\n",
"Downloading (…)neration_config.json: 100% 137/137 [00:00<00:00, 814kB/s]\n",
"\n",
"\n",
"\n",
"Downloading (…)fdb7a/.gitattributes: 100% 1.48k/1.48k [00:00<00:00, 11.4MB/s]\n",
"Fetching 11 files: 9% 1/11 [00:00<00:01, 9.05it/s]\n",
"\n",
"\n",
"Downloading (…)cial_tokens_map.json: 100% 411/411 [00:00<00:00, 1.57MB/s]\n",
"\n",
"\n",
"\n",
"Downloading (…)82a55fdb7a/README.md: 100% 8.34k/8.34k [00:00<00:00, 24.1MB/s]\n",
"\n",
"Downloading (…)l-00001-of-00002.bin: 0% 10.5M/9.98G [00:00<01:36, 103MB/s]\u001b[A\n",
"\n",
"\n",
"Downloading tokenizer.model: 0% 0.00/500k [00:00<?, ?B/s]\u001b[A\u001b[A\u001b[A\n",
"\n",
"\n",
"\n",
"Downloading (…)fdb7a/tokenizer.json: 0% 0.00/1.84M [00:00<?, ?B/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
"\n",
"Downloading tokenizer.model: 100% 500k/500k [00:00<00:00, 11.7MB/s]\n",
"Downloading (…)fdb7a/tokenizer.json: 100% 1.84M/1.84M [00:00<00:00, 28.3MB/s]\n",
"\n",
"Downloading (…)l-00001-of-00002.bin: 0% 41.9M/9.98G [00:00<00:55, 180MB/s]\u001b[A\n",
"\n",
"\n",
"Downloading (…)model.bin.index.json: 100% 26.8k/26.8k [00:00<00:00, 53.1MB/s]\n",
"\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 1% 21.0M/3.50G [00:00<00:44, 78.4MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 1% 73.4M/9.98G [00:00<00:50, 197MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 1% 31.5M/3.50G [00:00<00:47, 73.0MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 1% 94.4M/9.98G [00:00<00:49, 200MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 1% 41.9M/3.50G [00:00<00:44, 77.4MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 1% 115M/9.98G [00:00<00:49, 200MB/s] \u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 1% 52.4M/3.50G [00:00<00:42, 80.7MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 1% 136M/9.98G [00:00<00:49, 200MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 2% 62.9M/3.50G [00:00<00:42, 81.0MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 2% 168M/9.98G [00:00<00:47, 206MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 2% 73.4M/3.50G [00:00<00:40, 83.7MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 2% 199M/9.98G [00:00<00:46, 210MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 2% 83.9M/3.50G [00:01<00:39, 85.9MB/s]\u001b[A\u001b[A\n",
"\n",
"\n",
"Downloading (…)okenizer_config.json: 100% 727/727 [00:00<00:00, 3.07MB/s]\n",
"\n",
"Downloading (…)l-00001-of-00002.bin: 2% 231M/9.98G [00:01<00:45, 212MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 3% 94.4M/3.50G [00:01<00:40, 83.6MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 3% 262M/9.98G [00:01<00:45, 212MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 3% 105M/3.50G [00:01<00:42, 80.7MB/s] \u001b[A\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 3% 115M/3.50G [00:01<00:40, 83.3MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 3% 294M/9.98G [00:01<00:45, 214MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 4% 126M/3.50G [00:01<00:40, 84.0MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 3% 325M/9.98G [00:01<00:44, 216MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 4% 136M/3.50G [00:01<00:40, 83.7MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 4% 357M/9.98G [00:01<00:44, 216MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 4% 147M/3.50G [00:01<00:40, 82.3MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 4% 388M/9.98G [00:01<00:44, 215MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 4% 157M/3.50G [00:01<00:39, 83.7MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 4% 419M/9.98G [00:02<00:44, 213MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 5% 168M/3.50G [00:02<00:40, 82.8MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 5% 451M/9.98G [00:02<00:44, 214MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 5% 178M/3.50G [00:02<00:40, 82.3MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 5% 189M/3.50G [00:02<00:40, 81.9MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 5% 482M/9.98G [00:02<00:44, 211MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 6% 199M/3.50G [00:02<00:40, 81.1MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 5% 514M/9.98G [00:02<00:44, 214MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 6% 210M/3.50G [00:02<00:41, 80.0MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 5% 545M/9.98G [00:02<00:42, 220MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 6% 220M/3.50G [00:02<00:41, 78.3MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 6% 577M/9.98G [00:02<00:42, 220MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 7% 231M/3.50G [00:02<00:41, 79.1MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 7% 241M/3.50G [00:02<00:40, 79.8MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 7% 252M/3.50G [00:03<00:40, 79.6MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 6% 608M/9.98G [00:03<01:04, 145MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 6% 629M/9.98G [00:03<01:01, 153MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 7% 262M/3.50G [00:03<00:41, 77.4MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 7% 650M/9.98G [00:03<00:57, 161MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 8% 273M/3.50G [00:03<00:40, 79.8MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 7% 671M/9.98G [00:03<00:54, 171MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 8% 283M/3.50G [00:03<00:41, 77.8MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 7% 692M/9.98G [00:03<00:53, 174MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 8% 294M/3.50G [00:03<00:40, 78.9MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 7% 713M/9.98G [00:03<00:53, 172MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 9% 304M/3.50G [00:03<00:39, 81.4MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 7% 734M/9.98G [00:03<00:56, 165MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 9% 315M/3.50G [00:03<00:39, 80.0MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 8% 755M/9.98G [00:03<00:57, 161MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 9% 325M/3.50G [00:04<00:38, 82.5MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 8% 776M/9.98G [00:04<00:59, 154MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 10% 336M/3.50G [00:04<00:38, 83.0MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 8% 797M/9.98G [00:04<00:56, 164MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 10% 346M/3.50G [00:04<00:37, 84.2MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 10% 357M/3.50G [00:04<00:36, 85.1MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 8% 818M/9.98G [00:04<01:04, 143MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 10% 367M/3.50G [00:07<04:22, 11.9MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 11% 377M/3.50G [00:07<03:34, 14.5MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 8% 839M/9.98G [00:07<07:14, 21.0MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 11% 398M/3.50G [00:07<02:06, 24.6MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 9% 860M/9.98G [00:07<05:26, 27.9MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 12% 409M/3.50G [00:07<01:43, 30.0MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 9% 881M/9.98G [00:07<04:15, 35.7MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 12% 419M/3.50G [00:07<01:27, 35.2MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 12% 430M/3.50G [00:07<01:13, 41.9MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 9% 902M/9.98G [00:07<03:23, 44.6MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 13% 440M/3.50G [00:08<01:02, 49.0MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 13% 451M/3.50G [00:08<00:54, 56.0MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 9% 923M/9.98G [00:08<02:48, 53.7MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 13% 461M/3.50G [00:08<00:48, 62.1MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 9% 944M/9.98G [00:08<02:23, 63.0MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 13% 472M/3.50G [00:08<00:46, 65.2MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 14% 482M/3.50G [00:08<00:43, 69.7MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 10% 965M/9.98G [00:08<02:05, 72.0MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 14% 493M/3.50G [00:08<00:41, 71.9MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 10% 986M/9.98G [00:08<01:55, 77.9MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 14% 503M/3.50G [00:08<00:39, 76.4MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 10% 996M/9.98G [00:08<01:52, 79.7MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 15% 514M/3.50G [00:08<00:38, 77.2MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 10% 1.01G/9.98G [00:09<01:48, 82.6MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 15% 524M/3.50G [00:09<00:38, 76.8MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 10% 1.02G/9.98G [00:09<01:46, 84.1MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 15% 535M/3.50G [00:09<00:38, 77.9MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 10% 1.03G/9.98G [00:09<01:42, 87.1MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 16% 545M/3.50G [00:09<00:36, 81.3MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 10% 1.04G/9.98G [00:09<01:39, 89.5MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 16% 556M/3.50G [00:09<00:36, 79.6MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 11% 1.06G/9.98G [00:09<01:26, 104MB/s] \u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 16% 566M/3.50G [00:09<00:37, 79.2MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 11% 1.08G/9.98G [00:09<01:13, 121MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 16% 577M/3.50G [00:09<00:36, 79.7MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 11% 1.11G/9.98G [00:09<00:59, 150MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 17% 587M/3.50G [00:09<00:35, 82.0MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 11% 1.14G/9.98G [00:12<05:28, 26.9MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 12% 1.16G/9.98G [00:12<04:13, 34.7MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 17% 598M/3.50G [00:12<04:14, 11.4MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 17% 608M/3.50G [00:12<03:09, 15.2MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 12% 1.18G/9.98G [00:12<03:37, 40.5MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 18% 629M/3.50G [00:12<01:50, 25.9MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 19% 650M/3.50G [00:13<01:12, 39.4MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 12% 1.21G/9.98G [00:13<03:04, 47.5MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 19% 682M/3.50G [00:13<00:44, 63.2MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 12% 1.22G/9.98G [00:13<02:49, 51.8MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 20% 713M/3.50G [00:13<00:31, 88.4MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 12% 1.23G/9.98G [00:13<02:37, 55.5MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 21% 734M/3.50G [00:13<00:27, 101MB/s] \u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 12% 1.24G/9.98G [00:13<02:25, 60.0MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 13% 1.25G/9.98G [00:13<02:15, 64.5MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 22% 755M/3.50G [00:13<00:30, 90.4MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 13% 1.26G/9.98G [00:13<02:09, 67.4MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 13% 1.27G/9.98G [00:13<02:06, 68.8MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 22% 776M/3.50G [00:14<00:32, 83.5MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 13% 1.28G/9.98G [00:14<02:03, 70.6MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 13% 1.29G/9.98G [00:14<01:57, 73.9MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 23% 797M/3.50G [00:14<00:30, 87.4MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 13% 1.30G/9.98G [00:14<01:51, 77.5MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 23% 818M/3.50G [00:14<00:26, 102MB/s] \u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 13% 1.31G/9.98G [00:14<01:54, 76.0MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 24% 839M/3.50G [00:14<00:23, 115MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 25% 860M/3.50G [00:14<00:24, 108MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 13% 1.32G/9.98G [00:14<02:42, 53.1MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 25% 881M/3.50G [00:14<00:21, 123MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 13% 1.33G/9.98G [00:14<02:30, 57.5MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 26% 902M/3.50G [00:14<00:19, 135MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 26% 923M/3.50G [00:15<00:17, 148MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 14% 1.35G/9.98G [00:15<01:53, 75.8MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 27% 944M/3.50G [00:15<00:16, 158MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 14% 1.37G/9.98G [00:15<01:37, 88.7MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 28% 965M/3.50G [00:15<00:15, 164MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 14% 1.38G/9.98G [00:15<01:40, 85.8MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 28% 986M/3.50G [00:15<00:15, 167MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 29% 1.01G/3.50G [00:15<00:14, 171MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 14% 1.39G/9.98G [00:15<01:40, 85.4MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 29% 1.03G/3.50G [00:15<00:13, 177MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 14% 1.41G/9.98G [00:15<01:37, 87.6MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 30% 1.05G/3.50G [00:15<00:13, 176MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 14% 1.42G/9.98G [00:15<01:38, 86.8MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 31% 1.07G/3.50G [00:15<00:13, 181MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 14% 1.43G/9.98G [00:15<01:40, 85.3MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 14% 1.44G/9.98G [00:16<01:39, 86.0MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 31% 1.09G/3.50G [00:16<00:15, 160MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 15% 1.45G/9.98G [00:16<01:39, 85.9MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 15% 1.46G/9.98G [00:16<01:38, 86.4MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 32% 1.11G/3.50G [00:16<00:18, 129MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 15% 1.47G/9.98G [00:16<01:53, 75.2MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 32% 1.13G/3.50G [00:16<00:21, 110MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 15% 1.48G/9.98G [00:16<01:54, 74.0MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 15% 1.49G/9.98G [00:16<01:50, 76.9MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 33% 1.15G/3.50G [00:16<00:23, 101MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 15% 1.50G/9.98G [00:16<01:45, 80.4MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 15% 1.51G/9.98G [00:16<01:42, 82.4MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 34% 1.17G/3.50G [00:17<00:24, 96.6MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 15% 1.52G/9.98G [00:17<01:41, 83.5MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 15% 1.53G/9.98G [00:17<01:41, 83.0MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 34% 1.20G/3.50G [00:17<00:24, 93.7MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 15% 1.54G/9.98G [00:17<01:39, 84.4MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 34% 1.21G/3.50G [00:17<00:25, 90.8MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 16% 1.55G/9.98G [00:17<01:39, 84.3MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 35% 1.22G/3.50G [00:17<00:25, 90.5MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 16% 1.56G/9.98G [00:17<01:40, 83.9MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 35% 1.23G/3.50G [00:17<00:26, 85.8MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 16% 1.57G/9.98G [00:17<01:39, 84.2MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 35% 1.24G/3.50G [00:17<00:26, 85.8MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 16% 1.58G/9.98G [00:17<01:38, 85.4MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 36% 1.25G/3.50G [00:17<00:26, 86.3MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 16% 1.59G/9.98G [00:17<01:37, 85.6MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 36% 1.26G/3.50G [00:18<00:25, 88.0MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 16% 1.60G/9.98G [00:18<01:38, 85.2MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 36% 1.27G/3.50G [00:18<00:25, 88.6MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 16% 1.61G/9.98G [00:18<01:39, 83.8MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 37% 1.28G/3.50G [00:18<00:25, 88.5MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 16% 1.63G/9.98G [00:18<01:38, 85.2MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 37% 1.29G/3.50G [00:18<00:24, 88.6MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 16% 1.64G/9.98G [00:18<01:39, 83.5MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 37% 1.30G/3.50G [00:18<00:25, 88.0MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 17% 1.65G/9.98G [00:18<01:36, 85.9MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 37% 1.31G/3.50G [00:18<00:24, 88.1MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 17% 1.66G/9.98G [00:18<01:38, 84.8MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 38% 1.32G/3.50G [00:18<00:25, 86.1MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 17% 1.67G/9.98G [00:18<01:37, 85.6MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 38% 1.33G/3.50G [00:18<00:24, 87.6MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 17% 1.68G/9.98G [00:18<01:37, 85.5MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 38% 1.34G/3.50G [00:18<00:25, 84.7MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 17% 1.69G/9.98G [00:19<01:38, 84.0MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 39% 1.35G/3.50G [00:19<00:25, 85.7MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 17% 1.70G/9.98G [00:19<01:38, 84.3MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 39% 1.36G/3.50G [00:19<00:25, 83.4MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 17% 1.71G/9.98G [00:19<01:37, 84.8MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 39% 1.37G/3.50G [00:19<00:26, 79.2MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 17% 1.72G/9.98G [00:19<01:41, 81.0MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 40% 1.38G/3.50G [00:19<00:26, 81.2MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 17% 1.73G/9.98G [00:19<01:39, 82.9MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 40% 1.39G/3.50G [00:19<00:25, 82.4MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 17% 1.74G/9.98G [00:19<01:37, 84.1MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 40% 1.41G/3.50G [00:19<00:25, 81.8MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 18% 1.75G/9.98G [00:19<01:35, 86.4MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 40% 1.42G/3.50G [00:19<00:24, 83.8MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 18% 1.76G/9.98G [00:19<01:33, 87.5MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 41% 1.43G/3.50G [00:19<00:24, 84.7MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 18% 1.77G/9.98G [00:20<01:37, 84.1MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 41% 1.44G/3.50G [00:20<00:24, 84.6MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 18% 1.78G/9.98G [00:20<01:36, 85.3MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 41% 1.45G/3.50G [00:20<00:23, 85.8MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 18% 1.79G/9.98G [00:20<01:34, 86.4MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 42% 1.46G/3.50G [00:20<00:23, 86.5MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 18% 1.80G/9.98G [00:20<01:34, 86.9MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 42% 1.47G/3.50G [00:20<00:23, 85.7MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 18% 1.81G/9.98G [00:20<01:34, 86.5MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 42% 1.48G/3.50G [00:20<00:23, 84.6MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 18% 1.82G/9.98G [00:20<01:36, 84.6MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 43% 1.49G/3.50G [00:20<00:24, 83.3MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 18% 1.84G/9.98G [00:20<01:53, 72.0MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 43% 1.50G/3.50G [00:20<00:24, 83.0MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 18% 1.85G/9.98G [00:20<01:49, 74.1MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 43% 1.51G/3.50G [00:20<00:24, 81.0MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 43% 1.52G/3.50G [00:21<00:23, 83.0MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 19% 1.86G/9.98G [00:21<01:54, 70.8MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 44% 1.53G/3.50G [00:21<00:23, 83.8MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 19% 1.87G/9.98G [00:21<01:47, 75.3MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 44% 1.54G/3.50G [00:21<00:23, 84.6MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 19% 1.88G/9.98G [00:21<01:53, 71.3MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 44% 1.55G/3.50G [00:21<00:22, 87.2MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 19% 1.89G/9.98G [00:21<01:47, 75.2MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 45% 1.56G/3.50G [00:21<00:22, 88.0MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 19% 1.90G/9.98G [00:21<01:41, 79.8MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 45% 1.57G/3.50G [00:21<00:22, 87.5MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 19% 1.91G/9.98G [00:21<01:38, 82.2MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 45% 1.58G/3.50G [00:21<00:22, 83.7MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 19% 1.92G/9.98G [00:21<01:39, 81.1MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 46% 1.59G/3.50G [00:21<00:23, 80.4MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 19% 1.93G/9.98G [00:22<01:47, 74.6MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 46% 1.60G/3.50G [00:22<00:23, 82.2MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 19% 1.94G/9.98G [00:22<01:45, 76.1MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 46% 1.61G/3.50G [00:22<00:22, 84.0MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 20% 1.95G/9.98G [00:22<01:42, 78.3MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 46% 1.63G/3.50G [00:22<00:22, 84.4MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 20% 1.96G/9.98G [00:22<01:41, 78.6MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 47% 1.64G/3.50G [00:22<00:23, 80.9MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 20% 1.97G/9.98G [00:22<01:40, 79.9MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 47% 1.65G/3.50G [00:22<00:22, 83.2MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 20% 1.98G/9.98G [00:22<01:39, 80.4MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 47% 1.66G/3.50G [00:22<00:21, 84.1MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 20% 1.99G/9.98G [00:22<01:37, 81.9MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 48% 1.67G/3.50G [00:22<00:21, 84.6MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 48% 1.68G/3.50G [00:22<00:22, 82.8MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 20% 2.00G/9.98G [00:23<01:41, 78.4MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 48% 1.69G/3.50G [00:23<00:21, 84.7MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 20% 2.01G/9.98G [00:23<01:46, 74.8MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 49% 1.70G/3.50G [00:23<00:22, 81.3MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 20% 2.02G/9.98G [00:23<01:48, 73.2MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 49% 1.71G/3.50G [00:23<00:22, 80.5MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 49% 1.72G/3.50G [00:23<00:21, 81.7MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 20% 2.03G/9.98G [00:23<02:03, 64.5MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 49% 1.73G/3.50G [00:23<00:21, 83.8MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 20% 2.04G/9.98G [00:23<01:53, 69.6MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 50% 1.74G/3.50G [00:23<00:20, 84.3MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 21% 2.06G/9.98G [00:23<01:50, 71.4MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 50% 1.75G/3.50G [00:23<00:20, 85.5MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 21% 2.07G/9.98G [00:23<01:49, 72.6MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 50% 1.76G/3.50G [00:23<00:19, 87.3MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 21% 2.08G/9.98G [00:24<01:45, 75.2MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 51% 1.77G/3.50G [00:24<00:20, 85.0MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 21% 2.09G/9.98G [00:24<01:42, 77.3MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 51% 1.78G/3.50G [00:24<00:20, 85.8MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 21% 2.10G/9.98G [00:24<01:50, 71.1MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 51% 1.79G/3.50G [00:24<00:19, 85.4MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 52% 1.80G/3.50G [00:24<00:19, 87.0MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 21% 2.11G/9.98G [00:24<01:45, 74.2MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 52% 1.81G/3.50G [00:24<00:19, 85.8MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 21% 2.12G/9.98G [00:24<01:43, 75.8MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 52% 1.82G/3.50G [00:24<00:19, 84.4MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 21% 2.13G/9.98G [00:24<01:47, 73.1MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 52% 1.84G/3.50G [00:24<00:19, 83.4MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 21% 2.14G/9.98G [00:24<01:42, 76.2MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 53% 1.85G/3.50G [00:24<00:20, 81.7MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 22% 2.15G/9.98G [00:25<01:45, 73.9MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 53% 1.86G/3.50G [00:25<00:20, 81.8MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 22% 2.16G/9.98G [00:25<01:42, 76.5MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 53% 1.87G/3.50G [00:25<00:20, 80.3MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 22% 2.17G/9.98G [00:25<01:40, 77.7MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 54% 1.88G/3.50G [00:25<00:19, 82.6MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 22% 2.18G/9.98G [00:25<01:38, 79.2MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 54% 1.89G/3.50G [00:25<00:19, 84.3MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 22% 2.19G/9.98G [00:25<01:38, 79.0MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 54% 1.90G/3.50G [00:25<00:18, 85.7MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 22% 2.20G/9.98G [00:25<01:39, 78.2MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 55% 1.91G/3.50G [00:25<00:19, 82.3MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 22% 2.21G/9.98G [00:25<01:41, 76.2MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 55% 1.92G/3.50G [00:25<00:18, 84.2MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 22% 2.22G/9.98G [00:25<01:40, 77.5MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 55% 1.93G/3.50G [00:25<00:18, 85.3MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 22% 2.23G/9.98G [00:26<01:36, 79.8MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 55% 1.94G/3.50G [00:26<00:19, 81.8MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 22% 2.24G/9.98G [00:26<01:36, 80.0MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 56% 1.95G/3.50G [00:26<00:19, 81.5MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 23% 2.25G/9.98G [00:26<01:34, 81.6MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 56% 1.96G/3.50G [00:26<00:18, 82.6MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 23% 2.26G/9.98G [00:26<01:36, 79.8MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 56% 1.97G/3.50G [00:26<00:18, 82.0MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 23% 2.28G/9.98G [00:26<01:35, 80.2MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 57% 1.98G/3.50G [00:26<00:18, 82.5MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 23% 2.29G/9.98G [00:26<01:38, 78.4MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 57% 1.99G/3.50G [00:26<00:18, 81.8MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 23% 2.30G/9.98G [00:26<01:35, 80.1MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 57% 2.00G/3.50G [00:26<00:17, 83.8MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 58% 2.01G/3.50G [00:26<00:17, 84.5MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 23% 2.31G/9.98G [00:27<01:39, 77.0MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 58% 2.02G/3.50G [00:27<00:17, 82.7MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 23% 2.32G/9.98G [00:27<01:43, 74.1MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 58% 2.03G/3.50G [00:27<00:18, 77.9MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 23% 2.33G/9.98G [00:27<01:49, 69.9MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 58% 2.04G/3.50G [00:27<00:19, 76.3MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 23% 2.34G/9.98G [00:27<01:46, 71.5MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 59% 2.06G/3.50G [00:27<00:18, 79.8MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 24% 2.35G/9.98G [00:27<01:37, 77.9MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 59% 2.07G/3.50G [00:27<00:17, 82.2MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 24% 2.37G/9.98G [00:27<01:14, 102MB/s] \u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 59% 2.08G/3.50G [00:27<00:17, 81.0MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 24% 2.39G/9.98G [00:27<01:00, 125MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 60% 2.09G/3.50G [00:27<00:17, 81.5MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 24% 2.41G/9.98G [00:27<00:52, 145MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 24% 2.43G/9.98G [00:28<00:46, 162MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 60% 2.10G/3.50G [00:28<00:16, 83.3MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 25% 2.45G/9.98G [00:28<00:43, 173MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 60% 2.11G/3.50G [00:28<00:16, 85.1MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 25% 2.47G/9.98G [00:28<00:42, 175MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 25% 2.51G/9.98G [00:28<00:39, 190MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 61% 2.12G/3.50G [00:28<00:24, 56.9MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 25% 2.54G/9.98G [00:28<00:37, 201MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 61% 2.14G/3.50G [00:28<00:16, 82.9MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 26% 2.57G/9.98G [00:28<00:36, 205MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 26% 2.59G/9.98G [00:28<00:35, 205MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 62% 2.16G/3.50G [00:28<00:14, 90.8MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 26% 2.62G/9.98G [00:28<00:34, 212MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 62% 2.17G/3.50G [00:28<00:14, 88.9MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 62% 2.18G/3.50G [00:29<00:14, 89.3MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 27% 2.65G/9.98G [00:29<00:34, 214MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 63% 2.19G/3.50G [00:29<00:14, 87.4MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 27% 2.68G/9.98G [00:29<00:36, 201MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 63% 2.20G/3.50G [00:29<00:14, 86.9MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 27% 2.71G/9.98G [00:29<00:39, 183MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 63% 2.21G/3.50G [00:29<00:14, 87.8MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 64% 2.22G/3.50G [00:29<00:14, 85.7MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 27% 2.73G/9.98G [00:29<00:42, 171MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 64% 2.23G/3.50G [00:29<00:14, 86.3MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 28% 2.75G/9.98G [00:29<00:46, 156MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 64% 2.24G/3.50G [00:29<00:14, 86.6MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 28% 2.77G/9.98G [00:29<00:44, 160MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 64% 2.25G/3.50G [00:29<00:14, 85.0MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 28% 2.79G/9.98G [00:29<00:44, 160MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 65% 2.26G/3.50G [00:30<00:14, 85.4MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 28% 2.81G/9.98G [00:32<04:32, 26.3MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 65% 2.28G/3.50G [00:32<01:37, 12.6MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 28% 2.83G/9.98G [00:32<03:25, 34.7MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 65% 2.29G/3.50G [00:32<01:12, 16.8MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 66% 2.31G/3.50G [00:32<00:41, 28.7MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 29% 2.85G/9.98G [00:32<02:55, 40.7MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 67% 2.33G/3.50G [00:32<00:26, 43.4MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 29% 2.88G/9.98G [00:32<01:59, 59.6MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 67% 2.35G/3.50G [00:33<00:19, 58.9MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 29% 2.90G/9.98G [00:33<01:50, 64.3MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 68% 2.37G/3.50G [00:33<00:17, 63.8MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 29% 2.93G/9.98G [00:33<01:40, 70.4MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 68% 2.39G/3.50G [00:33<00:15, 71.1MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 30% 2.95G/9.98G [00:33<01:36, 72.9MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 69% 2.41G/3.50G [00:33<00:14, 73.4MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 69% 2.42G/3.50G [00:33<00:14, 74.6MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 30% 2.97G/9.98G [00:33<01:31, 76.3MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 69% 2.43G/3.50G [00:34<00:13, 76.8MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 30% 2.98G/9.98G [00:34<01:31, 76.3MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 70% 2.44G/3.50G [00:34<00:13, 78.6MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 30% 2.99G/9.98G [00:34<01:28, 78.6MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 30% 3.00G/9.98G [00:34<01:24, 82.7MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 70% 2.46G/3.50G [00:34<00:11, 87.9MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 30% 3.02G/9.98G [00:34<01:12, 96.0MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 71% 2.49G/3.50G [00:34<00:10, 101MB/s] \u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 30% 3.04G/9.98G [00:34<01:01, 113MB/s] \u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 72% 2.51G/3.50G [00:34<00:08, 119MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 31% 3.06G/9.98G [00:34<00:53, 129MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 72% 2.53G/3.50G [00:34<00:07, 136MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 31% 3.08G/9.98G [00:34<00:48, 143MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 73% 2.55G/3.50G [00:34<00:06, 148MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 31% 3.10G/9.98G [00:34<00:43, 158MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 73% 2.57G/3.50G [00:34<00:05, 158MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 31% 3.12G/9.98G [00:35<00:44, 152MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 74% 2.59G/3.50G [00:35<00:05, 158MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 32% 3.15G/9.98G [00:35<00:57, 119MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 75% 2.61G/3.50G [00:35<00:08, 107MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 32% 3.17G/9.98G [00:35<01:12, 94.2MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 75% 2.63G/3.50G [00:35<00:09, 95.6MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 32% 3.19G/9.98G [00:35<01:02, 109MB/s] \u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 76% 2.65G/3.50G [00:35<00:07, 108MB/s] \u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 32% 3.21G/9.98G [00:35<00:53, 125MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 76% 2.67G/3.50G [00:35<00:06, 122MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 32% 3.23G/9.98G [00:36<00:48, 139MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 77% 2.69G/3.50G [00:36<00:05, 134MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 33% 3.25G/9.98G [00:36<00:43, 154MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 78% 2.72G/3.50G [00:36<00:05, 147MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 33% 3.27G/9.98G [00:36<00:40, 165MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 78% 2.74G/3.50G [00:36<00:04, 158MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 33% 3.29G/9.98G [00:36<00:39, 170MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 79% 2.76G/3.50G [00:36<00:04, 167MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 33% 3.31G/9.98G [00:36<00:37, 176MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 79% 2.78G/3.50G [00:36<00:04, 174MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 33% 3.33G/9.98G [00:36<00:36, 183MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 80% 2.80G/3.50G [00:36<00:03, 177MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 34% 3.36G/9.98G [00:36<00:35, 186MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 81% 2.82G/3.50G [00:36<00:04, 148MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 34% 3.38G/9.98G [00:36<00:41, 159MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 34% 3.40G/9.98G [00:36<00:39, 168MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 34% 3.42G/9.98G [00:37<00:36, 177MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 81% 2.84G/3.50G [00:37<00:05, 117MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 34% 3.44G/9.98G [00:37<00:36, 177MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 35% 3.46G/9.98G [00:37<00:35, 181MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 82% 2.86G/3.50G [00:37<00:06, 104MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 35% 3.48G/9.98G [00:37<00:37, 173MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 35% 3.51G/9.98G [00:37<00:37, 172MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 82% 2.88G/3.50G [00:37<00:06, 91.3MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 35% 3.53G/9.98G [00:37<00:39, 164MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 83% 2.90G/3.50G [00:37<00:06, 93.8MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 36% 3.55G/9.98G [00:37<00:46, 139MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 83% 2.92G/3.50G [00:38<00:06, 91.5MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 36% 3.58G/9.98G [00:38<00:46, 138MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 84% 2.93G/3.50G [00:38<00:06, 85.1MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 36% 3.60G/9.98G [00:38<00:46, 138MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 84% 2.94G/3.50G [00:38<00:06, 83.5MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 84% 2.95G/3.50G [00:38<00:06, 83.3MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 36% 3.62G/9.98G [00:38<00:45, 140MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 84% 2.96G/3.50G [00:38<00:06, 79.9MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 36% 3.64G/9.98G [00:38<00:46, 137MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 85% 2.97G/3.50G [00:38<00:06, 81.1MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 37% 3.66G/9.98G [00:38<00:46, 137MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 85% 2.98G/3.50G [00:38<00:06, 79.8MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 37% 3.68G/9.98G [00:38<00:47, 132MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 85% 2.99G/3.50G [00:38<00:06, 82.0MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 86% 3.00G/3.50G [00:39<00:05, 83.9MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 37% 3.70G/9.98G [00:39<00:50, 123MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 86% 3.01G/3.50G [00:39<00:06, 77.7MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 37% 3.72G/9.98G [00:39<01:03, 99.2MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 38% 3.74G/9.98G [00:39<01:00, 103MB/s] \u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 86% 3.02G/3.50G [00:39<00:10, 47.1MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 38% 3.76G/9.98G [00:39<00:59, 105MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 87% 3.03G/3.50G [00:39<00:09, 48.7MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 38% 3.79G/9.98G [00:39<00:52, 118MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 87% 3.04G/3.50G [00:39<00:08, 56.9MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 38% 3.81G/9.98G [00:40<00:47, 130MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 87% 3.06G/3.50G [00:40<00:05, 77.3MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 38% 3.83G/9.98G [00:40<00:42, 145MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 39% 3.85G/9.98G [00:40<00:39, 154MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 88% 3.08G/3.50G [00:40<00:04, 94.1MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 39% 3.87G/9.98G [00:40<00:37, 161MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 89% 3.10G/3.50G [00:40<00:03, 111MB/s] \u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 39% 3.89G/9.98G [00:40<00:35, 170MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 39% 3.91G/9.98G [00:40<00:34, 178MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 89% 3.12G/3.50G [00:40<00:03, 109MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 39% 3.93G/9.98G [00:40<00:33, 182MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 40% 3.95G/9.98G [00:40<00:31, 190MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 90% 3.15G/3.50G [00:40<00:03, 102MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 40% 3.97G/9.98G [00:40<00:31, 193MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 40% 4.00G/9.98G [00:41<00:33, 180MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 90% 3.17G/3.50G [00:41<00:03, 96.2MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 91% 3.18G/3.50G [00:41<00:03, 93.8MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 40% 4.02G/9.98G [00:41<00:38, 156MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 40% 4.04G/9.98G [00:41<00:36, 163MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 91% 3.19G/3.50G [00:41<00:03, 90.4MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 41% 4.06G/9.98G [00:41<00:33, 175MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 91% 3.20G/3.50G [00:41<00:03, 89.5MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 41% 4.08G/9.98G [00:41<00:33, 178MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 92% 3.21G/3.50G [00:41<00:03, 89.3MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 41% 4.10G/9.98G [00:41<00:33, 175MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 92% 3.22G/3.50G [00:41<00:03, 87.3MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 41% 4.12G/9.98G [00:41<00:34, 172MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 92% 3.23G/3.50G [00:41<00:03, 87.9MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 42% 4.14G/9.98G [00:41<00:34, 170MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 93% 3.24G/3.50G [00:41<00:02, 87.6MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 42% 4.16G/9.98G [00:42<00:32, 177MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 93% 3.25G/3.50G [00:42<00:02, 86.1MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 42% 4.18G/9.98G [00:42<00:34, 170MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 93% 3.26G/3.50G [00:42<00:02, 85.4MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 42% 4.20G/9.98G [00:42<00:34, 168MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 93% 3.27G/3.50G [00:42<00:02, 82.2MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 42% 4.23G/9.98G [00:42<00:34, 169MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 94% 3.28G/3.50G [00:42<00:02, 83.5MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 43% 4.25G/9.98G [00:42<00:34, 166MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 94% 3.29G/3.50G [00:42<00:02, 80.2MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 43% 4.27G/9.98G [00:42<00:34, 166MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 94% 3.30G/3.50G [00:42<00:02, 81.6MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 43% 4.29G/9.98G [00:42<00:36, 158MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 95% 3.31G/3.50G [00:42<00:02, 78.9MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 43% 4.31G/9.98G [00:42<00:37, 150MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 95% 3.32G/3.50G [00:42<00:02, 80.4MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 95% 3.33G/3.50G [00:43<00:02, 81.3MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 43% 4.33G/9.98G [00:43<00:44, 128MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 96% 3.34G/3.50G [00:43<00:01, 82.3MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 44% 4.35G/9.98G [00:43<00:41, 137MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 96% 3.36G/3.50G [00:43<00:01, 79.2MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 44% 4.37G/9.98G [00:43<00:41, 135MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 96% 3.37G/3.50G [00:43<00:01, 82.1MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 96% 3.38G/3.50G [00:43<00:01, 83.2MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 44% 4.39G/9.98G [00:43<00:40, 137MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 97% 3.39G/3.50G [00:43<00:01, 82.6MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 44% 4.41G/9.98G [00:43<00:40, 136MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 97% 3.40G/3.50G [00:43<00:01, 84.6MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 44% 4.44G/9.98G [00:43<00:40, 135MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 97% 3.41G/3.50G [00:43<00:01, 84.9MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 98% 3.42G/3.50G [00:44<00:00, 84.8MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 45% 4.46G/9.98G [00:44<00:42, 131MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 98% 3.43G/3.50G [00:44<00:00, 84.5MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 45% 4.48G/9.98G [00:44<00:43, 125MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 98% 3.44G/3.50G [00:44<00:00, 85.1MB/s]\u001b[A\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 99% 3.45G/3.50G [00:44<00:00, 83.5MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 45% 4.50G/9.98G [00:44<00:46, 119MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 99% 3.46G/3.50G [00:44<00:00, 84.2MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 45% 4.52G/9.98G [00:44<00:44, 123MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 99% 3.47G/3.50G [00:44<00:00, 83.9MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 46% 4.54G/9.98G [00:44<00:43, 124MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 99% 3.48G/3.50G [00:44<00:00, 80.4MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 46% 4.56G/9.98G [00:44<00:39, 138MB/s]\u001b[A\n",
"\n",
"Downloading (…)l-00002-of-00002.bin: 100% 3.49G/3.50G [00:45<00:00, 81.6MB/s]\u001b[A\u001b[A\n",
"Downloading (…)l-00002-of-00002.bin: 100% 3.50G/3.50G [00:45<00:00, 77.6MB/s]\n",
"\n",
"Downloading (…)l-00001-of-00002.bin: 46% 4.60G/9.98G [00:45<00:41, 129MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 46% 4.62G/9.98G [00:45<00:40, 134MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 47% 4.65G/9.98G [00:45<00:36, 148MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 47% 4.67G/9.98G [00:45<00:32, 162MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 47% 4.70G/9.98G [00:45<00:29, 179MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 47% 4.72G/9.98G [00:45<00:28, 185MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 48% 4.75G/9.98G [00:46<00:26, 196MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 48% 4.77G/9.98G [00:46<00:26, 198MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 48% 4.79G/9.98G [00:46<00:25, 201MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 48% 4.82G/9.98G [00:46<00:25, 205MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 49% 4.85G/9.98G [00:46<00:24, 207MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 49% 4.89G/9.98G [00:46<00:24, 209MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 49% 4.91G/9.98G [00:46<00:24, 208MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 50% 4.94G/9.98G [00:46<00:23, 211MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 50% 4.97G/9.98G [00:47<00:23, 214MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 50% 5.00G/9.98G [00:47<00:26, 187MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 50% 5.02G/9.98G [00:47<00:27, 180MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 51% 5.05G/9.98G [00:47<00:25, 192MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 51% 5.09G/9.98G [00:47<00:24, 200MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 51% 5.12G/9.98G [00:47<00:23, 206MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 52% 5.15G/9.98G [00:47<00:22, 210MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 52% 5.18G/9.98G [00:48<00:22, 215MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 52% 5.21G/9.98G [00:48<00:21, 218MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 53% 5.24G/9.98G [00:48<00:21, 220MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 53% 5.27G/9.98G [00:48<00:21, 219MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 53% 5.31G/9.98G [00:48<00:21, 218MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 53% 5.34G/9.98G [00:48<00:21, 217MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 54% 5.37G/9.98G [00:48<00:21, 213MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 54% 5.40G/9.98G [00:49<00:30, 149MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 54% 5.42G/9.98G [00:49<00:29, 157MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 55% 5.44G/9.98G [00:49<00:27, 164MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 55% 5.46G/9.98G [00:49<00:26, 170MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 55% 5.48G/9.98G [00:49<00:25, 178MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 55% 5.52G/9.98G [00:49<00:23, 190MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 56% 5.55G/9.98G [00:50<00:22, 200MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 56% 5.58G/9.98G [00:50<00:21, 208MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 56% 5.61G/9.98G [00:50<00:20, 211MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 57% 5.64G/9.98G [00:50<00:20, 214MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 57% 5.67G/9.98G [00:50<00:19, 219MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 57% 5.70G/9.98G [00:50<00:19, 220MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 57% 5.74G/9.98G [00:50<00:19, 216MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 58% 5.77G/9.98G [00:51<00:19, 217MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 58% 5.80G/9.98G [00:51<00:19, 219MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 58% 5.83G/9.98G [00:51<00:18, 220MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 59% 5.86G/9.98G [00:51<00:21, 194MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 59% 5.88G/9.98G [00:51<00:21, 194MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 59% 5.90G/9.98G [00:51<00:21, 192MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 59% 5.92G/9.98G [00:51<00:21, 193MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 60% 5.95G/9.98G [00:51<00:20, 196MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 60% 5.97G/9.98G [00:52<00:20, 193MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 60% 5.99G/9.98G [00:52<00:20, 193MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 60% 6.01G/9.98G [00:52<00:20, 196MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 60% 6.03G/9.98G [00:52<00:20, 197MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 61% 6.06G/9.98G [00:52<00:18, 207MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 61% 6.09G/9.98G [00:52<00:18, 210MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 61% 6.12G/9.98G [00:52<00:18, 211MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 62% 6.16G/9.98G [00:53<00:20, 187MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 62% 6.18G/9.98G [00:53<00:21, 175MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 62% 6.21G/9.98G [00:53<00:20, 188MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 63% 6.24G/9.98G [00:53<00:19, 196MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 63% 6.27G/9.98G [00:53<00:18, 204MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 63% 6.30G/9.98G [00:53<00:17, 208MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 63% 6.33G/9.98G [00:53<00:17, 210MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 64% 6.36G/9.98G [00:54<00:17, 209MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 64% 6.40G/9.98G [00:54<00:17, 207MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 64% 6.42G/9.98G [00:54<00:17, 203MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 65% 6.44G/9.98G [00:54<00:17, 204MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 65% 6.46G/9.98G [00:54<00:17, 203MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 65% 6.48G/9.98G [00:54<00:17, 201MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 65% 6.50G/9.98G [00:54<00:18, 188MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 65% 6.52G/9.98G [00:54<00:18, 190MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 66% 6.54G/9.98G [00:54<00:18, 191MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 66% 6.56G/9.98G [00:55<00:20, 168MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 66% 6.59G/9.98G [00:55<00:20, 168MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 66% 6.61G/9.98G [00:55<00:19, 175MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 66% 6.63G/9.98G [00:55<00:18, 183MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 67% 6.66G/9.98G [00:55<00:17, 194MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 67% 6.69G/9.98G [00:55<00:16, 203MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 67% 6.72G/9.98G [00:55<00:15, 208MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 68% 6.74G/9.98G [00:56<00:15, 209MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 68% 6.77G/9.98G [00:56<00:15, 212MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 68% 6.81G/9.98G [00:56<00:15, 211MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 69% 6.84G/9.98G [00:56<00:15, 206MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 69% 6.86G/9.98G [00:56<00:15, 205MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 69% 6.88G/9.98G [00:56<00:15, 204MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 69% 6.90G/9.98G [00:56<00:15, 198MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 69% 6.93G/9.98G [00:56<00:14, 204MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 70% 6.95G/9.98G [00:57<00:15, 200MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 70% 6.97G/9.98G [00:57<00:16, 184MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 70% 6.99G/9.98G [00:57<00:18, 160MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 70% 7.01G/9.98G [00:57<00:19, 148MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 71% 7.04G/9.98G [00:57<00:19, 150MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 71% 7.07G/9.98G [00:57<00:17, 170MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 71% 7.10G/9.98G [00:57<00:15, 186MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 71% 7.13G/9.98G [00:58<00:14, 198MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 72% 7.16G/9.98G [00:58<00:13, 206MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 72% 7.19G/9.98G [00:58<00:13, 210MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 72% 7.22G/9.98G [00:58<00:12, 215MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 73% 7.26G/9.98G [00:58<00:12, 216MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 73% 7.29G/9.98G [00:58<00:12, 217MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 73% 7.32G/9.98G [00:58<00:12, 207MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 74% 7.35G/9.98G [00:59<00:12, 212MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 74% 7.38G/9.98G [00:59<00:14, 176MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 74% 7.40G/9.98G [00:59<00:17, 151MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 74% 7.42G/9.98G [00:59<00:17, 143MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 75% 7.44G/9.98G [00:59<00:18, 136MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 75% 7.47G/9.98G [01:00<00:20, 120MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 75% 7.49G/9.98G [01:00<00:26, 93.1MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 75% 7.51G/9.98G [01:00<00:33, 73.9MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 75% 7.53G/9.98G [01:01<00:28, 85.5MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 76% 7.54G/9.98G [01:01<00:27, 87.9MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 76% 7.55G/9.98G [01:01<00:27, 87.5MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 76% 7.57G/9.98G [01:01<00:27, 87.0MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 76% 7.58G/9.98G [01:01<00:26, 89.3MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 76% 7.60G/9.98G [01:01<00:22, 108MB/s] \u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 76% 7.62G/9.98G [01:01<00:19, 124MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 77% 7.64G/9.98G [01:02<00:16, 139MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 77% 7.67G/9.98G [01:02<00:15, 151MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 77% 7.69G/9.98G [01:02<00:14, 163MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 77% 7.72G/9.98G [01:02<00:12, 180MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 78% 7.74G/9.98G [01:02<00:12, 180MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 78% 7.77G/9.98G [01:02<00:11, 191MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 78% 7.80G/9.98G [01:02<00:10, 200MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 79% 7.83G/9.98G [01:02<00:10, 205MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 79% 7.86G/9.98G [01:03<00:10, 206MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 79% 7.89G/9.98G [01:03<00:11, 181MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 79% 7.92G/9.98G [01:03<00:10, 192MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 80% 7.94G/9.98G [01:03<00:10, 195MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 80% 7.97G/9.98G [01:03<00:09, 203MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 80% 8.00G/9.98G [01:03<00:09, 210MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 81% 8.03G/9.98G [01:03<00:09, 213MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 81% 8.06G/9.98G [01:04<00:09, 212MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 81% 8.10G/9.98G [01:04<00:08, 209MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 81% 8.13G/9.98G [01:04<00:09, 201MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 82% 8.15G/9.98G [01:04<00:09, 191MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 82% 8.17G/9.98G [01:04<00:09, 193MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 82% 8.19G/9.98G [01:04<00:09, 184MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 82% 8.21G/9.98G [01:04<00:09, 177MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 83% 8.23G/9.98G [01:05<00:09, 180MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 83% 8.25G/9.98G [01:05<00:11, 145MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 83% 8.27G/9.98G [01:05<00:11, 151MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 83% 8.29G/9.98G [01:05<00:10, 162MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 83% 8.33G/9.98G [01:05<00:09, 181MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 84% 8.36G/9.98G [01:05<00:08, 195MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 84% 8.39G/9.98G [01:05<00:07, 203MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 84% 8.41G/9.98G [01:05<00:07, 203MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 85% 8.44G/9.98G [01:06<00:07, 210MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 85% 8.47G/9.98G [01:06<00:07, 213MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 85% 8.50G/9.98G [01:06<00:06, 211MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 86% 8.54G/9.98G [01:06<00:07, 204MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 86% 8.56G/9.98G [01:06<00:07, 202MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 86% 8.59G/9.98G [01:06<00:06, 207MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 86% 8.62G/9.98G [01:06<00:06, 208MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 87% 8.65G/9.98G [01:07<00:06, 207MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 87% 8.67G/9.98G [01:07<00:06, 206MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 87% 8.70G/9.98G [01:07<00:06, 211MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 88% 8.73G/9.98G [01:07<00:05, 214MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 88% 8.77G/9.98G [01:07<00:05, 217MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 88% 8.80G/9.98G [01:07<00:05, 217MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 88% 8.83G/9.98G [01:08<00:05, 192MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 89% 8.85G/9.98G [01:08<00:05, 194MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 89% 8.87G/9.98G [01:08<00:05, 192MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 89% 8.89G/9.98G [01:08<00:05, 194MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 89% 8.91G/9.98G [01:08<00:05, 193MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 90% 8.93G/9.98G [01:08<00:05, 198MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 90% 8.95G/9.98G [01:08<00:05, 195MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 90% 8.98G/9.98G [01:08<00:05, 193MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 90% 9.00G/9.98G [01:08<00:05, 187MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 90% 9.02G/9.98G [01:09<00:05, 186MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 91% 9.04G/9.98G [01:09<00:05, 172MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 91% 9.06G/9.98G [01:09<00:05, 171MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 91% 9.08G/9.98G [01:09<00:05, 176MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 91% 9.10G/9.98G [01:09<00:06, 131MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 91% 9.12G/9.98G [01:10<00:09, 92.4MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 92% 9.14G/9.98G [01:10<00:08, 97.1MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 92% 9.16G/9.98G [01:10<00:07, 112MB/s] \u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 92% 9.19G/9.98G [01:10<00:06, 127MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 92% 9.21G/9.98G [01:10<00:06, 120MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 92% 9.23G/9.98G [01:10<00:07, 100MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 93% 9.25G/9.98G [01:11<00:07, 91.3MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 93% 9.27G/9.98G [01:11<00:06, 108MB/s] \u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 93% 9.29G/9.98G [01:11<00:07, 87.6MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 93% 9.31G/9.98G [01:11<00:06, 100MB/s] \u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 94% 9.33G/9.98G [01:11<00:05, 116MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 94% 9.35G/9.98G [01:12<00:04, 133MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 94% 9.37G/9.98G [01:12<00:04, 149MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 94% 9.41G/9.98G [01:12<00:03, 167MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 94% 9.43G/9.98G [01:12<00:03, 172MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 95% 9.45G/9.98G [01:12<00:02, 177MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 95% 9.48G/9.98G [01:12<00:02, 191MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 95% 9.50G/9.98G [01:12<00:02, 194MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 96% 9.53G/9.98G [01:12<00:02, 199MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 96% 9.55G/9.98G [01:12<00:02, 201MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 96% 9.57G/9.98G [01:13<00:02, 192MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 96% 9.59G/9.98G [01:13<00:02, 169MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 96% 9.63G/9.98G [01:13<00:01, 185MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 97% 9.66G/9.98G [01:13<00:01, 194MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 97% 9.69G/9.98G [01:13<00:01, 200MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 97% 9.72G/9.98G [01:13<00:01, 207MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 98% 9.75G/9.98G [01:14<00:01, 211MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 98% 9.78G/9.98G [01:14<00:00, 212MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 98% 9.81G/9.98G [01:14<00:00, 205MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 99% 9.84G/9.98G [01:14<00:00, 206MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 99% 9.86G/9.98G [01:14<00:00, 205MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 99% 9.88G/9.98G [01:14<00:00, 200MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 99% 9.90G/9.98G [01:14<00:00, 199MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 99% 9.92G/9.98G [01:14<00:00, 195MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 100% 9.94G/9.98G [01:14<00:00, 190MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00002.bin: 100% 9.98G/9.98G [01:15<00:00, 132MB/s]\n",
"Fetching 11 files: 100% 11/11 [01:15<00:00, 6.86s/it]\n",
"Loading ckpt pytorch_model-00001-of-00002.bin\n",
"copying base_model.model.model.embed_tokens.weight from 0-th LoRA weight to model.embed_tokens.weight\n",
"merging base_model.model.model.layers.0.self_attn.q_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.0.self_attn.q_proj.weight\n",
"merging base_model.model.model.layers.0.self_attn.k_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.0.self_attn.k_proj.weight\n",
"merging base_model.model.model.layers.0.self_attn.v_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.0.self_attn.v_proj.weight\n",
"merging base_model.model.model.layers.0.self_attn.o_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.0.self_attn.o_proj.weight\n",
"merging base_model.model.model.layers.0.mlp.gate_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.0.mlp.gate_proj.weight\n",
"merging base_model.model.model.layers.0.mlp.down_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.0.mlp.down_proj.weight\n",
"merging base_model.model.model.layers.0.mlp.up_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.0.mlp.up_proj.weight\n",
"merging base_model.model.model.layers.1.self_attn.q_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.1.self_attn.q_proj.weight\n",
"merging base_model.model.model.layers.1.self_attn.k_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.1.self_attn.k_proj.weight\n",
"merging base_model.model.model.layers.1.self_attn.v_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.1.self_attn.v_proj.weight\n",
"merging base_model.model.model.layers.1.self_attn.o_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.1.self_attn.o_proj.weight\n",
"merging base_model.model.model.layers.1.mlp.gate_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.1.mlp.gate_proj.weight\n",
"merging base_model.model.model.layers.1.mlp.down_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.1.mlp.down_proj.weight\n",
"merging base_model.model.model.layers.1.mlp.up_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.1.mlp.up_proj.weight\n",
"merging base_model.model.model.layers.2.self_attn.q_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.2.self_attn.q_proj.weight\n",
"merging base_model.model.model.layers.2.self_attn.k_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.2.self_attn.k_proj.weight\n",
"merging base_model.model.model.layers.2.self_attn.v_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.2.self_attn.v_proj.weight\n",
"merging base_model.model.model.layers.2.self_attn.o_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.2.self_attn.o_proj.weight\n",
"merging base_model.model.model.layers.2.mlp.gate_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.2.mlp.gate_proj.weight\n",
"merging base_model.model.model.layers.2.mlp.down_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.2.mlp.down_proj.weight\n",
"merging base_model.model.model.layers.2.mlp.up_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.2.mlp.up_proj.weight\n",
"merging base_model.model.model.layers.3.self_attn.q_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.3.self_attn.q_proj.weight\n",
"merging base_model.model.model.layers.3.self_attn.k_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.3.self_attn.k_proj.weight\n",
"merging base_model.model.model.layers.3.self_attn.v_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.3.self_attn.v_proj.weight\n",
"merging base_model.model.model.layers.3.self_attn.o_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.3.self_attn.o_proj.weight\n",
"merging base_model.model.model.layers.3.mlp.gate_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.3.mlp.gate_proj.weight\n",
"merging base_model.model.model.layers.3.mlp.down_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.3.mlp.down_proj.weight\n",
"merging base_model.model.model.layers.3.mlp.up_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.3.mlp.up_proj.weight\n",
"merging base_model.model.model.layers.4.self_attn.q_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.4.self_attn.q_proj.weight\n",
"merging base_model.model.model.layers.4.self_attn.k_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.4.self_attn.k_proj.weight\n",
"merging base_model.model.model.layers.4.self_attn.v_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.4.self_attn.v_proj.weight\n",
"merging base_model.model.model.layers.4.self_attn.o_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.4.self_attn.o_proj.weight\n",
"merging base_model.model.model.layers.4.mlp.gate_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.4.mlp.gate_proj.weight\n",
"merging base_model.model.model.layers.4.mlp.down_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.4.mlp.down_proj.weight\n",
"merging base_model.model.model.layers.4.mlp.up_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.4.mlp.up_proj.weight\n",
"merging base_model.model.model.layers.5.self_attn.q_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.5.self_attn.q_proj.weight\n",
"merging base_model.model.model.layers.5.self_attn.k_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.5.self_attn.k_proj.weight\n",
"merging base_model.model.model.layers.5.self_attn.v_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.5.self_attn.v_proj.weight\n",
"merging base_model.model.model.layers.5.self_attn.o_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.5.self_attn.o_proj.weight\n",
"merging base_model.model.model.layers.5.mlp.gate_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.5.mlp.gate_proj.weight\n",
"merging base_model.model.model.layers.5.mlp.down_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.5.mlp.down_proj.weight\n",
"merging base_model.model.model.layers.5.mlp.up_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.5.mlp.up_proj.weight\n",
"merging base_model.model.model.layers.6.self_attn.q_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.6.self_attn.q_proj.weight\n",
"merging base_model.model.model.layers.6.self_attn.k_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.6.self_attn.k_proj.weight\n",
"merging base_model.model.model.layers.6.self_attn.v_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.6.self_attn.v_proj.weight\n",
"merging base_model.model.model.layers.6.self_attn.o_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.6.self_attn.o_proj.weight\n",
"merging base_model.model.model.layers.6.mlp.gate_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.6.mlp.gate_proj.weight\n",
"merging base_model.model.model.layers.6.mlp.down_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.6.mlp.down_proj.weight\n",
"merging base_model.model.model.layers.6.mlp.up_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.6.mlp.up_proj.weight\n",
"merging base_model.model.model.layers.7.self_attn.q_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.7.self_attn.q_proj.weight\n",
"merging base_model.model.model.layers.7.self_attn.k_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.7.self_attn.k_proj.weight\n",
"merging base_model.model.model.layers.7.self_attn.v_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.7.self_attn.v_proj.weight\n",
"merging base_model.model.model.layers.7.self_attn.o_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.7.self_attn.o_proj.weight\n",
"merging base_model.model.model.layers.7.mlp.gate_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.7.mlp.gate_proj.weight\n",
"merging base_model.model.model.layers.7.mlp.down_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.7.mlp.down_proj.weight\n",
"merging base_model.model.model.layers.7.mlp.up_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.7.mlp.up_proj.weight\n",
"merging base_model.model.model.layers.8.self_attn.q_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.8.self_attn.q_proj.weight\n",
"merging base_model.model.model.layers.8.self_attn.k_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.8.self_attn.k_proj.weight\n",
"merging base_model.model.model.layers.8.self_attn.v_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.8.self_attn.v_proj.weight\n",
"merging base_model.model.model.layers.8.self_attn.o_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.8.self_attn.o_proj.weight\n",
"merging base_model.model.model.layers.8.mlp.gate_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.8.mlp.gate_proj.weight\n",
"merging base_model.model.model.layers.8.mlp.down_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.8.mlp.down_proj.weight\n",
"merging base_model.model.model.layers.8.mlp.up_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.8.mlp.up_proj.weight\n",
"merging base_model.model.model.layers.9.self_attn.q_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.9.self_attn.q_proj.weight\n",
"merging base_model.model.model.layers.9.self_attn.k_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.9.self_attn.k_proj.weight\n",
"merging base_model.model.model.layers.9.self_attn.v_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.9.self_attn.v_proj.weight\n",
"merging base_model.model.model.layers.9.self_attn.o_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.9.self_attn.o_proj.weight\n",
"merging base_model.model.model.layers.9.mlp.gate_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.9.mlp.gate_proj.weight\n",
"merging base_model.model.model.layers.9.mlp.down_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.9.mlp.down_proj.weight\n",
"merging base_model.model.model.layers.9.mlp.up_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.9.mlp.up_proj.weight\n",
"merging base_model.model.model.layers.10.self_attn.q_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.10.self_attn.q_proj.weight\n",
"merging base_model.model.model.layers.10.self_attn.k_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.10.self_attn.k_proj.weight\n",
"merging base_model.model.model.layers.10.self_attn.v_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.10.self_attn.v_proj.weight\n",
"merging base_model.model.model.layers.10.self_attn.o_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.10.self_attn.o_proj.weight\n",
"merging base_model.model.model.layers.10.mlp.gate_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.10.mlp.gate_proj.weight\n",
"merging base_model.model.model.layers.10.mlp.down_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.10.mlp.down_proj.weight\n",
"merging base_model.model.model.layers.10.mlp.up_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.10.mlp.up_proj.weight\n",
"merging base_model.model.model.layers.11.self_attn.q_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.11.self_attn.q_proj.weight\n",
"merging base_model.model.model.layers.11.self_attn.k_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.11.self_attn.k_proj.weight\n",
"merging base_model.model.model.layers.11.self_attn.v_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.11.self_attn.v_proj.weight\n",
"merging base_model.model.model.layers.11.self_attn.o_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.11.self_attn.o_proj.weight\n",
"merging base_model.model.model.layers.11.mlp.gate_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.11.mlp.gate_proj.weight\n",
"merging base_model.model.model.layers.11.mlp.down_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.11.mlp.down_proj.weight\n",
"merging base_model.model.model.layers.11.mlp.up_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.11.mlp.up_proj.weight\n",
"merging base_model.model.model.layers.12.self_attn.q_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.12.self_attn.q_proj.weight\n",
"merging base_model.model.model.layers.12.self_attn.k_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.12.self_attn.k_proj.weight\n",
"merging base_model.model.model.layers.12.self_attn.v_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.12.self_attn.v_proj.weight\n",
"merging base_model.model.model.layers.12.self_attn.o_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.12.self_attn.o_proj.weight\n",
"merging base_model.model.model.layers.12.mlp.gate_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.12.mlp.gate_proj.weight\n",
"merging base_model.model.model.layers.12.mlp.down_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.12.mlp.down_proj.weight\n",
"merging base_model.model.model.layers.12.mlp.up_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.12.mlp.up_proj.weight\n",
"merging base_model.model.model.layers.13.self_attn.q_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.13.self_attn.q_proj.weight\n",
"merging base_model.model.model.layers.13.self_attn.k_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.13.self_attn.k_proj.weight\n",
"merging base_model.model.model.layers.13.self_attn.v_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.13.self_attn.v_proj.weight\n",
"merging base_model.model.model.layers.13.self_attn.o_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.13.self_attn.o_proj.weight\n",
"merging base_model.model.model.layers.13.mlp.gate_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.13.mlp.gate_proj.weight\n",
"merging base_model.model.model.layers.13.mlp.down_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.13.mlp.down_proj.weight\n",
"merging base_model.model.model.layers.13.mlp.up_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.13.mlp.up_proj.weight\n",
"merging base_model.model.model.layers.14.self_attn.q_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.14.self_attn.q_proj.weight\n",
"merging base_model.model.model.layers.14.self_attn.k_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.14.self_attn.k_proj.weight\n",
"merging base_model.model.model.layers.14.self_attn.v_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.14.self_attn.v_proj.weight\n",
"merging base_model.model.model.layers.14.self_attn.o_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.14.self_attn.o_proj.weight\n",
"merging base_model.model.model.layers.14.mlp.gate_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.14.mlp.gate_proj.weight\n",
"merging base_model.model.model.layers.14.mlp.down_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.14.mlp.down_proj.weight\n",
"merging base_model.model.model.layers.14.mlp.up_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.14.mlp.up_proj.weight\n",
"merging base_model.model.model.layers.15.self_attn.q_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.15.self_attn.q_proj.weight\n",
"merging base_model.model.model.layers.15.self_attn.k_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.15.self_attn.k_proj.weight\n",
"merging base_model.model.model.layers.15.self_attn.v_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.15.self_attn.v_proj.weight\n",
"merging base_model.model.model.layers.15.self_attn.o_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.15.self_attn.o_proj.weight\n",
"merging base_model.model.model.layers.15.mlp.gate_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.15.mlp.gate_proj.weight\n",
"merging base_model.model.model.layers.15.mlp.down_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.15.mlp.down_proj.weight\n",
"merging base_model.model.model.layers.15.mlp.up_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.15.mlp.up_proj.weight\n",
"merging base_model.model.model.layers.16.self_attn.q_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.16.self_attn.q_proj.weight\n",
"merging base_model.model.model.layers.16.self_attn.k_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.16.self_attn.k_proj.weight\n",
"merging base_model.model.model.layers.16.self_attn.v_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.16.self_attn.v_proj.weight\n",
"merging base_model.model.model.layers.16.self_attn.o_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.16.self_attn.o_proj.weight\n",
"merging base_model.model.model.layers.16.mlp.gate_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.16.mlp.gate_proj.weight\n",
"merging base_model.model.model.layers.16.mlp.down_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.16.mlp.down_proj.weight\n",
"merging base_model.model.model.layers.16.mlp.up_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.16.mlp.up_proj.weight\n",
"merging base_model.model.model.layers.17.self_attn.q_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.17.self_attn.q_proj.weight\n",
"merging base_model.model.model.layers.17.self_attn.k_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.17.self_attn.k_proj.weight\n",
"merging base_model.model.model.layers.17.self_attn.v_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.17.self_attn.v_proj.weight\n",
"merging base_model.model.model.layers.17.self_attn.o_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.17.self_attn.o_proj.weight\n",
"merging base_model.model.model.layers.17.mlp.gate_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.17.mlp.gate_proj.weight\n",
"merging base_model.model.model.layers.17.mlp.down_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.17.mlp.down_proj.weight\n",
"merging base_model.model.model.layers.17.mlp.up_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.17.mlp.up_proj.weight\n",
"merging base_model.model.model.layers.18.self_attn.q_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.18.self_attn.q_proj.weight\n",
"merging base_model.model.model.layers.18.self_attn.k_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.18.self_attn.k_proj.weight\n",
"merging base_model.model.model.layers.18.self_attn.v_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.18.self_attn.v_proj.weight\n",
"merging base_model.model.model.layers.18.self_attn.o_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.18.self_attn.o_proj.weight\n",
"merging base_model.model.model.layers.18.mlp.gate_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.18.mlp.gate_proj.weight\n",
"merging base_model.model.model.layers.18.mlp.down_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.18.mlp.down_proj.weight\n",
"merging base_model.model.model.layers.18.mlp.up_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.18.mlp.up_proj.weight\n",
"merging base_model.model.model.layers.19.self_attn.q_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.19.self_attn.q_proj.weight\n",
"merging base_model.model.model.layers.19.self_attn.k_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.19.self_attn.k_proj.weight\n",
"merging base_model.model.model.layers.19.self_attn.v_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.19.self_attn.v_proj.weight\n",
"merging base_model.model.model.layers.19.self_attn.o_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.19.self_attn.o_proj.weight\n",
"merging base_model.model.model.layers.19.mlp.gate_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.19.mlp.gate_proj.weight\n",
"merging base_model.model.model.layers.19.mlp.down_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.19.mlp.down_proj.weight\n",
"merging base_model.model.model.layers.19.mlp.up_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.19.mlp.up_proj.weight\n",
"merging base_model.model.model.layers.20.self_attn.q_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.20.self_attn.q_proj.weight\n",
"merging base_model.model.model.layers.20.self_attn.k_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.20.self_attn.k_proj.weight\n",
"merging base_model.model.model.layers.20.self_attn.v_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.20.self_attn.v_proj.weight\n",
"merging base_model.model.model.layers.20.self_attn.o_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.20.self_attn.o_proj.weight\n",
"merging base_model.model.model.layers.20.mlp.gate_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.20.mlp.gate_proj.weight\n",
"merging base_model.model.model.layers.20.mlp.down_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.20.mlp.down_proj.weight\n",
"merging base_model.model.model.layers.20.mlp.up_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.20.mlp.up_proj.weight\n",
"merging base_model.model.model.layers.21.self_attn.q_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.21.self_attn.q_proj.weight\n",
"merging base_model.model.model.layers.21.self_attn.k_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.21.self_attn.k_proj.weight\n",
"merging base_model.model.model.layers.21.self_attn.v_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.21.self_attn.v_proj.weight\n",
"merging base_model.model.model.layers.21.self_attn.o_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.21.self_attn.o_proj.weight\n",
"merging base_model.model.model.layers.21.mlp.gate_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.21.mlp.gate_proj.weight\n",
"merging base_model.model.model.layers.21.mlp.down_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.21.mlp.down_proj.weight\n",
"merging base_model.model.model.layers.21.mlp.up_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.21.mlp.up_proj.weight\n",
"merging base_model.model.model.layers.22.self_attn.q_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.22.self_attn.q_proj.weight\n",
"merging base_model.model.model.layers.22.self_attn.k_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.22.self_attn.k_proj.weight\n",
"merging base_model.model.model.layers.22.self_attn.v_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.22.self_attn.v_proj.weight\n",
"merging base_model.model.model.layers.22.self_attn.o_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.22.self_attn.o_proj.weight\n",
"merging base_model.model.model.layers.22.mlp.gate_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.22.mlp.gate_proj.weight\n",
"merging base_model.model.model.layers.22.mlp.down_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.22.mlp.down_proj.weight\n",
"merging base_model.model.model.layers.22.mlp.up_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.22.mlp.up_proj.weight\n",
"merging base_model.model.model.layers.23.self_attn.q_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.23.self_attn.q_proj.weight\n",
"merging base_model.model.model.layers.23.self_attn.k_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.23.self_attn.k_proj.weight\n",
"merging base_model.model.model.layers.23.self_attn.v_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.23.self_attn.v_proj.weight\n",
"merging base_model.model.model.layers.23.self_attn.o_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.23.self_attn.o_proj.weight\n",
"merging base_model.model.model.layers.23.mlp.gate_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.23.mlp.gate_proj.weight\n",
"merging base_model.model.model.layers.23.mlp.down_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.23.mlp.down_proj.weight\n",
"merging base_model.model.model.layers.23.mlp.up_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.23.mlp.up_proj.weight\n",
"Saving ckpt pytorch_model-00001-of-00002.bin to alpaca-combined in pth format...\n",
"Saving shard 1 of 1 into alpaca-combined/L1-consolidated.00.pth\n",
"Loading ckpt pytorch_model-00002-of-00002.bin\n",
"merging base_model.model.model.layers.24.self_attn.q_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.24.self_attn.q_proj.weight\n",
"merging base_model.model.model.layers.24.self_attn.k_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.24.self_attn.k_proj.weight\n",
"merging base_model.model.model.layers.24.self_attn.v_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.24.self_attn.v_proj.weight\n",
"merging base_model.model.model.layers.24.self_attn.o_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.24.self_attn.o_proj.weight\n",
"merging base_model.model.model.layers.24.mlp.gate_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.24.mlp.gate_proj.weight\n",
"merging base_model.model.model.layers.24.mlp.down_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.24.mlp.down_proj.weight\n",
"merging base_model.model.model.layers.24.mlp.up_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.24.mlp.up_proj.weight\n",
"merging base_model.model.model.layers.25.self_attn.q_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.25.self_attn.q_proj.weight\n",
"merging base_model.model.model.layers.25.self_attn.k_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.25.self_attn.k_proj.weight\n",
"merging base_model.model.model.layers.25.self_attn.v_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.25.self_attn.v_proj.weight\n",
"merging base_model.model.model.layers.25.self_attn.o_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.25.self_attn.o_proj.weight\n",
"merging base_model.model.model.layers.25.mlp.gate_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.25.mlp.gate_proj.weight\n",
"merging base_model.model.model.layers.25.mlp.down_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.25.mlp.down_proj.weight\n",
"merging base_model.model.model.layers.25.mlp.up_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.25.mlp.up_proj.weight\n",
"merging base_model.model.model.layers.26.self_attn.q_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.26.self_attn.q_proj.weight\n",
"merging base_model.model.model.layers.26.self_attn.k_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.26.self_attn.k_proj.weight\n",
"merging base_model.model.model.layers.26.self_attn.v_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.26.self_attn.v_proj.weight\n",
"merging base_model.model.model.layers.26.self_attn.o_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.26.self_attn.o_proj.weight\n",
"merging base_model.model.model.layers.26.mlp.gate_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.26.mlp.gate_proj.weight\n",
"merging base_model.model.model.layers.26.mlp.down_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.26.mlp.down_proj.weight\n",
"merging base_model.model.model.layers.26.mlp.up_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.26.mlp.up_proj.weight\n",
"merging base_model.model.model.layers.27.self_attn.q_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.27.self_attn.q_proj.weight\n",
"merging base_model.model.model.layers.27.self_attn.k_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.27.self_attn.k_proj.weight\n",
"merging base_model.model.model.layers.27.self_attn.v_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.27.self_attn.v_proj.weight\n",
"merging base_model.model.model.layers.27.self_attn.o_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.27.self_attn.o_proj.weight\n",
"merging base_model.model.model.layers.27.mlp.gate_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.27.mlp.gate_proj.weight\n",
"merging base_model.model.model.layers.27.mlp.down_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.27.mlp.down_proj.weight\n",
"merging base_model.model.model.layers.27.mlp.up_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.27.mlp.up_proj.weight\n",
"merging base_model.model.model.layers.28.self_attn.q_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.28.self_attn.q_proj.weight\n",
"merging base_model.model.model.layers.28.self_attn.k_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.28.self_attn.k_proj.weight\n",
"merging base_model.model.model.layers.28.self_attn.v_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.28.self_attn.v_proj.weight\n",
"merging base_model.model.model.layers.28.self_attn.o_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.28.self_attn.o_proj.weight\n",
"merging base_model.model.model.layers.28.mlp.gate_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.28.mlp.gate_proj.weight\n",
"merging base_model.model.model.layers.28.mlp.down_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.28.mlp.down_proj.weight\n",
"merging base_model.model.model.layers.28.mlp.up_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.28.mlp.up_proj.weight\n",
"merging base_model.model.model.layers.29.self_attn.q_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.29.self_attn.q_proj.weight\n",
"merging base_model.model.model.layers.29.self_attn.k_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.29.self_attn.k_proj.weight\n",
"merging base_model.model.model.layers.29.self_attn.v_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.29.self_attn.v_proj.weight\n",
"merging base_model.model.model.layers.29.self_attn.o_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.29.self_attn.o_proj.weight\n",
"merging base_model.model.model.layers.29.mlp.gate_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.29.mlp.gate_proj.weight\n",
"merging base_model.model.model.layers.29.mlp.down_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.29.mlp.down_proj.weight\n",
"merging base_model.model.model.layers.29.mlp.up_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.29.mlp.up_proj.weight\n",
"merging base_model.model.model.layers.30.self_attn.q_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.30.self_attn.q_proj.weight\n",
"merging base_model.model.model.layers.30.self_attn.k_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.30.self_attn.k_proj.weight\n",
"merging base_model.model.model.layers.30.self_attn.v_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.30.self_attn.v_proj.weight\n",
"merging base_model.model.model.layers.30.self_attn.o_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.30.self_attn.o_proj.weight\n",
"merging base_model.model.model.layers.30.mlp.gate_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.30.mlp.gate_proj.weight\n",
"merging base_model.model.model.layers.30.mlp.down_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.30.mlp.down_proj.weight\n",
"merging base_model.model.model.layers.30.mlp.up_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.30.mlp.up_proj.weight\n",
"merging base_model.model.model.layers.31.self_attn.q_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.31.self_attn.q_proj.weight\n",
"merging base_model.model.model.layers.31.self_attn.k_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.31.self_attn.k_proj.weight\n",
"merging base_model.model.model.layers.31.self_attn.v_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.31.self_attn.v_proj.weight\n",
"merging base_model.model.model.layers.31.self_attn.o_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.31.self_attn.o_proj.weight\n",
"merging base_model.model.model.layers.31.mlp.gate_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.31.mlp.gate_proj.weight\n",
"merging base_model.model.model.layers.31.mlp.down_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.31.mlp.down_proj.weight\n",
"merging base_model.model.model.layers.31.mlp.up_proj.lora_A.weight and lora_B.weight form 0-th LoRA weight to model.layers.31.mlp.up_proj.weight\n",
"copying base_model.model.lm_head.weight from 0-th LoRA weight to lm_head.weight\n",
"Saving ckpt pytorch_model-00002-of-00002.bin to alpaca-combined in pth format...\n",
"Saving shard 1 of 1 into alpaca-combined/L2-consolidated.00.pth\n",
"Saving tokenizer\n",
"Saving params.json into alpaca-combined/params.json\n",
"Loading ['L1-consolidated.00.pth', 'L2-consolidated.00.pth'] ...\n",
"Saving the merged shard to alpaca-combined/consolidated.00.pth\n",
"Cleaning up...\n",
"Done.\n"
]
}
]
},
{
"cell_type": "markdown",
"source": [
"## 比对SHA256\n",
"\n",
"完整值：https://github.com/ymcui/Chinese-LLaMA-Alpaca/blob/main/SHA256.md\n",
"\n",
"其中本示例生成的Alpaca-7B的标准SHA256：\n",
"- fbfccc91183169842aac8d093379f0a449b5a26c5ee7a298baf0d556f1499b90\n",
"\n",
"使用下述命令评测后发现两者相同，合并无误。"
],
"metadata": {
"id": "iO6f_kZOPB_q"
}
},
{
"cell_type": "code",
"source": [
"!sha256sum alpaca-combined/consolidated.*.pth"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "t5u4QDNZPYI_",
"outputId": "d0ceb9f9-b2bd-424d-eff7-b7e4dcb459d0"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"fbfccc91183169842aac8d093379f0a449b5a26c5ee7a298baf0d556f1499b90 alpaca-combined/consolidated.00.pth\n"
]
}
]
},
{
"cell_type": "markdown",
"source": [
"## 量化模型\n",
"接下来我们使用[llama.cpp](https://github.com/ggerganov/llama.cpp)工具对上一步生成的全量版本权重进行转换，生成4-bit量化模型。\n",
"\n",
"### 编译工具\n",
"\n",
"首先对llama.cpp工具进行编译。"
],
"metadata": {
"id": "ueexcKo-Q_EW"
}
},
{
"cell_type": "code",
"source": [
"!cd llama.cpp && make"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "_GbjsT2wRRCR",
"outputId": "2d66c72f-0ef1-4a56-eebb-1a658827e8e3"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"I llama.cpp build info: \n",
"I UNAME_S: Linux\n",
"I UNAME_P: x86_64\n",
"I UNAME_M: x86_64\n",
"I CFLAGS: -I. -O3 -std=c11 -fPIC -DNDEBUG -Wall -Wextra -Wpedantic -Wcast-qual -Wdouble-promotion -Wshadow -Wstrict-prototypes -Wpointer-arith -pthread -march=native -mtune=native -DGGML_USE_K_QUANTS\n",
"I CXXFLAGS: -I. -I./examples -O3 -std=c++11 -fPIC -DNDEBUG -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-multichar -pthread -march=native -mtune=native -DGGML_USE_K_QUANTS\n",
"I LDFLAGS: \n",
"I CC: cc (Ubuntu 9.4.0-1ubuntu1~20.04.1) 9.4.0\n",
"I CXX: g++ (Ubuntu 9.4.0-1ubuntu1~20.04.1) 9.4.0\n",
"\n",
"cc -I. -O3 -std=c11 -fPIC -DNDEBUG -Wall -Wextra -Wpedantic -Wcast-qual -Wdouble-promotion -Wshadow -Wstrict-prototypes -Wpointer-arith -pthread -march=native -mtune=native -DGGML_USE_K_QUANTS -c ggml.c -o ggml.o\n",
"g++ -I. -I./examples -O3 -std=c++11 -fPIC -DNDEBUG -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-multichar -pthread -march=native -mtune=native -DGGML_USE_K_QUANTS -c llama.cpp -o llama.o\n",
"\u001b[01m\u001b[Kllama.cpp:\u001b[m\u001b[K In function ‘\u001b[01m\u001b[Kbool kv_cache_init(const llama_hparams&, llama_kv_cache&, ggml_type, int, int)\u001b[m\u001b[K’:\n",
"\u001b[01m\u001b[Kllama.cpp:877:38:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[Kunused parameter ‘\u001b[01m\u001b[Kn_gpu_layers\u001b[m\u001b[K’ [\u001b[01;35m\u001b[K-Wunused-parameter\u001b[m\u001b[K]\n",
" 877 | \u001b[01;35m\u001b[Kint n_gpu_layers\u001b[m\u001b[K) {\n",
" | \u001b[01;35m\u001b[K~~~~~~^~~~~~~~~~~~\u001b[m\u001b[K\n",
"g++ -I. -I./examples -O3 -std=c++11 -fPIC -DNDEBUG -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-multichar -pthread -march=native -mtune=native -DGGML_USE_K_QUANTS -c examples/common.cpp -o common.o\n",
"cc -I. -O3 -std=c11 -fPIC -DNDEBUG -Wall -Wextra -Wpedantic -Wcast-qual -Wdouble-promotion -Wshadow -Wstrict-prototypes -Wpointer-arith -pthread -march=native -mtune=native -DGGML_USE_K_QUANTS -c -o k_quants.o k_quants.c\n",
"g++ -I. -I./examples -O3 -std=c++11 -fPIC -DNDEBUG -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-multichar -pthread -march=native -mtune=native -DGGML_USE_K_QUANTS examples/main/main.cpp ggml.o llama.o common.o k_quants.o -o main \n",
"\n",
"==== Run ./main -h for help. ====\n",
"\n",
"g++ -I. -I./examples -O3 -std=c++11 -fPIC -DNDEBUG -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-multichar -pthread -march=native -mtune=native -DGGML_USE_K_QUANTS examples/quantize/quantize.cpp ggml.o llama.o k_quants.o -o quantize \n",
"g++ -I. -I./examples -O3 -std=c++11 -fPIC -DNDEBUG -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-multichar -pthread -march=native -mtune=native -DGGML_USE_K_QUANTS examples/quantize-stats/quantize-stats.cpp ggml.o llama.o k_quants.o -o quantize-stats \n",
"g++ -I. -I./examples -O3 -std=c++11 -fPIC -DNDEBUG -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-multichar -pthread -march=native -mtune=native -DGGML_USE_K_QUANTS examples/perplexity/perplexity.cpp ggml.o llama.o common.o k_quants.o -o perplexity \n",
"g++ -I. -I./examples -O3 -std=c++11 -fPIC -DNDEBUG -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-multichar -pthread -march=native -mtune=native -DGGML_USE_K_QUANTS examples/embedding/embedding.cpp ggml.o llama.o common.o k_quants.o -o embedding \n",
"g++ -I. -I./examples -O3 -std=c++11 -fPIC -DNDEBUG -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-multichar -pthread -march=native -mtune=native -DGGML_USE_K_QUANTS pocs/vdot/vdot.cpp ggml.o k_quants.o -o vdot \n"
]
}
]
},
{
"cell_type": "markdown",
"source": [
"### 模型转换为ggml格式（FP16）\n",
"\n",
"这一步，我们将模型转换为ggml格式（FP16）。\n",
"- 在这之前需要把`alpaca-combined`目录挪个位置，把模型文件放到`llama.cpp/zh-models/7B`下，把`tokenizer.model`放到`llama.cpp/zh-models`\n",
"- tokenizer在哪里？\n",
" - `alpaca-combined`目录下有\n",
" - 或者从以下网址下载：https://huggingface.co/ziqingyang/chinese-alpaca-lora-7b/resolve/main/tokenizer.model （注意，Alpaca和LLaMA的`tokenizer.model`不能混用！）\n",
"\n",
"💡 转换13B/33B模型提示：\n",
"- tokenizer可以直接用7B的，13B/33B和7B的相同\n",
"- Alpaca和LLaMA的`tokenizer.model`不能混用！\n",
"- 以下看到7B字样的都是文件夹名，与转换过程没有关系了，改不改都行"
],
"metadata": {
"id": "gw2xpYC0RcQC"
}
},
{
"cell_type": "code",
"source": [
"!cd llama.cpp && mkdir zh-models && mv ../alpaca-combined zh-models/7B\n",
"!mv llama.cpp/zh-models/7B/tokenizer.model llama.cpp/zh-models/\n",
"!ls llama.cpp/zh-models/"
],
"metadata": {
"id": "5KgnFVStRjio",
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "02a9192c-941d-4636-befc-2d4c981d65e8"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"7B tokenizer.model\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"!cd llama.cpp && python convert.py zh-models/7B/"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "NUHeoTMQS1AQ",
"outputId": "95ec2886-a8c7-4537-9242-131f9d235f33"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Loading model file zh-models/7B/consolidated.00.pth\n",
"Loading vocab file zh-models/tokenizer.model\n",
"Writing vocab...\n",
"[ 1/291] Writing tensor tok_embeddings.weight | size 49954 x 4096 | type UnquantizedDataType(name='F16')\n",
"[ 2/291] Writing tensor norm.weight | size 4096 | type UnquantizedDataType(name='F32')\n",
"[ 3/291] Writing tensor output.weight | size 49954 x 4096 | type UnquantizedDataType(name='F16')\n",
"[ 4/291] Writing tensor layers.0.attention.wq.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[ 5/291] Writing tensor layers.0.attention.wk.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[ 6/291] Writing tensor layers.0.attention.wv.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[ 7/291] Writing tensor layers.0.attention.wo.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[ 8/291] Writing tensor layers.0.attention_norm.weight | size 4096 | type UnquantizedDataType(name='F32')\n",
"[ 9/291] Writing tensor layers.0.feed_forward.w1.weight | size 11008 x 4096 | type UnquantizedDataType(name='F16')\n",
"[ 10/291] Writing tensor layers.0.feed_forward.w2.weight | size 4096 x 11008 | type UnquantizedDataType(name='F16')\n",
"[ 11/291] Writing tensor layers.0.feed_forward.w3.weight | size 11008 x 4096 | type UnquantizedDataType(name='F16')\n",
"[ 12/291] Writing tensor layers.0.ffn_norm.weight | size 4096 | type UnquantizedDataType(name='F32')\n",
"[ 13/291] Writing tensor layers.1.attention.wq.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[ 14/291] Writing tensor layers.1.attention.wk.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[ 15/291] Writing tensor layers.1.attention.wv.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[ 16/291] Writing tensor layers.1.attention.wo.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[ 17/291] Writing tensor layers.1.attention_norm.weight | size 4096 | type UnquantizedDataType(name='F32')\n",
"[ 18/291] Writing tensor layers.1.feed_forward.w1.weight | size 11008 x 4096 | type UnquantizedDataType(name='F16')\n",
"[ 19/291] Writing tensor layers.1.feed_forward.w2.weight | size 4096 x 11008 | type UnquantizedDataType(name='F16')\n",
"[ 20/291] Writing tensor layers.1.feed_forward.w3.weight | size 11008 x 4096 | type UnquantizedDataType(name='F16')\n",
"[ 21/291] Writing tensor layers.1.ffn_norm.weight | size 4096 | type UnquantizedDataType(name='F32')\n",
"[ 22/291] Writing tensor layers.2.attention.wq.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[ 23/291] Writing tensor layers.2.attention.wk.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[ 24/291] Writing tensor layers.2.attention.wv.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[ 25/291] Writing tensor layers.2.attention.wo.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[ 26/291] Writing tensor layers.2.attention_norm.weight | size 4096 | type UnquantizedDataType(name='F32')\n",
"[ 27/291] Writing tensor layers.2.feed_forward.w1.weight | size 11008 x 4096 | type UnquantizedDataType(name='F16')\n",
"[ 28/291] Writing tensor layers.2.feed_forward.w2.weight | size 4096 x 11008 | type UnquantizedDataType(name='F16')\n",
"[ 29/291] Writing tensor layers.2.feed_forward.w3.weight | size 11008 x 4096 | type UnquantizedDataType(name='F16')\n",
"[ 30/291] Writing tensor layers.2.ffn_norm.weight | size 4096 | type UnquantizedDataType(name='F32')\n",
"[ 31/291] Writing tensor layers.3.attention.wq.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[ 32/291] Writing tensor layers.3.attention.wk.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[ 33/291] Writing tensor layers.3.attention.wv.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[ 34/291] Writing tensor layers.3.attention.wo.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[ 35/291] Writing tensor layers.3.attention_norm.weight | size 4096 | type UnquantizedDataType(name='F32')\n",
"[ 36/291] Writing tensor layers.3.feed_forward.w1.weight | size 11008 x 4096 | type UnquantizedDataType(name='F16')\n",
"[ 37/291] Writing tensor layers.3.feed_forward.w2.weight | size 4096 x 11008 | type UnquantizedDataType(name='F16')\n",
"[ 38/291] Writing tensor layers.3.feed_forward.w3.weight | size 11008 x 4096 | type UnquantizedDataType(name='F16')\n",
"[ 39/291] Writing tensor layers.3.ffn_norm.weight | size 4096 | type UnquantizedDataType(name='F32')\n",
"[ 40/291] Writing tensor layers.4.attention.wq.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[ 41/291] Writing tensor layers.4.attention.wk.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[ 42/291] Writing tensor layers.4.attention.wv.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[ 43/291] Writing tensor layers.4.attention.wo.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[ 44/291] Writing tensor layers.4.attention_norm.weight | size 4096 | type UnquantizedDataType(name='F32')\n",
"[ 45/291] Writing tensor layers.4.feed_forward.w1.weight | size 11008 x 4096 | type UnquantizedDataType(name='F16')\n",
"[ 46/291] Writing tensor layers.4.feed_forward.w2.weight | size 4096 x 11008 | type UnquantizedDataType(name='F16')\n",
"[ 47/291] Writing tensor layers.4.feed_forward.w3.weight | size 11008 x 4096 | type UnquantizedDataType(name='F16')\n",
"[ 48/291] Writing tensor layers.4.ffn_norm.weight | size 4096 | type UnquantizedDataType(name='F32')\n",
"[ 49/291] Writing tensor layers.5.attention.wq.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[ 50/291] Writing tensor layers.5.attention.wk.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[ 51/291] Writing tensor layers.5.attention.wv.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[ 52/291] Writing tensor layers.5.attention.wo.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[ 53/291] Writing tensor layers.5.attention_norm.weight | size 4096 | type UnquantizedDataType(name='F32')\n",
"[ 54/291] Writing tensor layers.5.feed_forward.w1.weight | size 11008 x 4096 | type UnquantizedDataType(name='F16')\n",
"[ 55/291] Writing tensor layers.5.feed_forward.w2.weight | size 4096 x 11008 | type UnquantizedDataType(name='F16')\n",
"[ 56/291] Writing tensor layers.5.feed_forward.w3.weight | size 11008 x 4096 | type UnquantizedDataType(name='F16')\n",
"[ 57/291] Writing tensor layers.5.ffn_norm.weight | size 4096 | type UnquantizedDataType(name='F32')\n",
"[ 58/291] Writing tensor layers.6.attention.wq.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[ 59/291] Writing tensor layers.6.attention.wk.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[ 60/291] Writing tensor layers.6.attention.wv.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[ 61/291] Writing tensor layers.6.attention.wo.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[ 62/291] Writing tensor layers.6.attention_norm.weight | size 4096 | type UnquantizedDataType(name='F32')\n",
"[ 63/291] Writing tensor layers.6.feed_forward.w1.weight | size 11008 x 4096 | type UnquantizedDataType(name='F16')\n",
"[ 64/291] Writing tensor layers.6.feed_forward.w2.weight | size 4096 x 11008 | type UnquantizedDataType(name='F16')\n",
"[ 65/291] Writing tensor layers.6.feed_forward.w3.weight | size 11008 x 4096 | type UnquantizedDataType(name='F16')\n",
"[ 66/291] Writing tensor layers.6.ffn_norm.weight | size 4096 | type UnquantizedDataType(name='F32')\n",
"[ 67/291] Writing tensor layers.7.attention.wq.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[ 68/291] Writing tensor layers.7.attention.wk.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[ 69/291] Writing tensor layers.7.attention.wv.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[ 70/291] Writing tensor layers.7.attention.wo.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[ 71/291] Writing tensor layers.7.attention_norm.weight | size 4096 | type UnquantizedDataType(name='F32')\n",
"[ 72/291] Writing tensor layers.7.feed_forward.w1.weight | size 11008 x 4096 | type UnquantizedDataType(name='F16')\n",
"[ 73/291] Writing tensor layers.7.feed_forward.w2.weight | size 4096 x 11008 | type UnquantizedDataType(name='F16')\n",
"[ 74/291] Writing tensor layers.7.feed_forward.w3.weight | size 11008 x 4096 | type UnquantizedDataType(name='F16')\n",
"[ 75/291] Writing tensor layers.7.ffn_norm.weight | size 4096 | type UnquantizedDataType(name='F32')\n",
"[ 76/291] Writing tensor layers.8.attention.wq.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[ 77/291] Writing tensor layers.8.attention.wk.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[ 78/291] Writing tensor layers.8.attention.wv.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[ 79/291] Writing tensor layers.8.attention.wo.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[ 80/291] Writing tensor layers.8.attention_norm.weight | size 4096 | type UnquantizedDataType(name='F32')\n",
"[ 81/291] Writing tensor layers.8.feed_forward.w1.weight | size 11008 x 4096 | type UnquantizedDataType(name='F16')\n",
"[ 82/291] Writing tensor layers.8.feed_forward.w2.weight | size 4096 x 11008 | type UnquantizedDataType(name='F16')\n",
"[ 83/291] Writing tensor layers.8.feed_forward.w3.weight | size 11008 x 4096 | type UnquantizedDataType(name='F16')\n",
"[ 84/291] Writing tensor layers.8.ffn_norm.weight | size 4096 | type UnquantizedDataType(name='F32')\n",
"[ 85/291] Writing tensor layers.9.attention.wq.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[ 86/291] Writing tensor layers.9.attention.wk.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[ 87/291] Writing tensor layers.9.attention.wv.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[ 88/291] Writing tensor layers.9.attention.wo.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[ 89/291] Writing tensor layers.9.attention_norm.weight | size 4096 | type UnquantizedDataType(name='F32')\n",
"[ 90/291] Writing tensor layers.9.feed_forward.w1.weight | size 11008 x 4096 | type UnquantizedDataType(name='F16')\n",
"[ 91/291] Writing tensor layers.9.feed_forward.w2.weight | size 4096 x 11008 | type UnquantizedDataType(name='F16')\n",
"[ 92/291] Writing tensor layers.9.feed_forward.w3.weight | size 11008 x 4096 | type UnquantizedDataType(name='F16')\n",
"[ 93/291] Writing tensor layers.9.ffn_norm.weight | size 4096 | type UnquantizedDataType(name='F32')\n",
"[ 94/291] Writing tensor layers.10.attention.wq.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[ 95/291] Writing tensor layers.10.attention.wk.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[ 96/291] Writing tensor layers.10.attention.wv.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[ 97/291] Writing tensor layers.10.attention.wo.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[ 98/291] Writing tensor layers.10.attention_norm.weight | size 4096 | type UnquantizedDataType(name='F32')\n",
"[ 99/291] Writing tensor layers.10.feed_forward.w1.weight | size 11008 x 4096 | type UnquantizedDataType(name='F16')\n",
"[100/291] Writing tensor layers.10.feed_forward.w2.weight | size 4096 x 11008 | type UnquantizedDataType(name='F16')\n",
"[101/291] Writing tensor layers.10.feed_forward.w3.weight | size 11008 x 4096 | type UnquantizedDataType(name='F16')\n",
"[102/291] Writing tensor layers.10.ffn_norm.weight | size 4096 | type UnquantizedDataType(name='F32')\n",
"[103/291] Writing tensor layers.11.attention.wq.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[104/291] Writing tensor layers.11.attention.wk.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[105/291] Writing tensor layers.11.attention.wv.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[106/291] Writing tensor layers.11.attention.wo.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[107/291] Writing tensor layers.11.attention_norm.weight | size 4096 | type UnquantizedDataType(name='F32')\n",
"[108/291] Writing tensor layers.11.feed_forward.w1.weight | size 11008 x 4096 | type UnquantizedDataType(name='F16')\n",
"[109/291] Writing tensor layers.11.feed_forward.w2.weight | size 4096 x 11008 | type UnquantizedDataType(name='F16')\n",
"[110/291] Writing tensor layers.11.feed_forward.w3.weight | size 11008 x 4096 | type UnquantizedDataType(name='F16')\n",
"[111/291] Writing tensor layers.11.ffn_norm.weight | size 4096 | type UnquantizedDataType(name='F32')\n",
"[112/291] Writing tensor layers.12.attention.wq.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[113/291] Writing tensor layers.12.attention.wk.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[114/291] Writing tensor layers.12.attention.wv.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[115/291] Writing tensor layers.12.attention.wo.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[116/291] Writing tensor layers.12.attention_norm.weight | size 4096 | type UnquantizedDataType(name='F32')\n",
"[117/291] Writing tensor layers.12.feed_forward.w1.weight | size 11008 x 4096 | type UnquantizedDataType(name='F16')\n",
"[118/291] Writing tensor layers.12.feed_forward.w2.weight | size 4096 x 11008 | type UnquantizedDataType(name='F16')\n",
"[119/291] Writing tensor layers.12.feed_forward.w3.weight | size 11008 x 4096 | type UnquantizedDataType(name='F16')\n",
"[120/291] Writing tensor layers.12.ffn_norm.weight | size 4096 | type UnquantizedDataType(name='F32')\n",
"[121/291] Writing tensor layers.13.attention.wq.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[122/291] Writing tensor layers.13.attention.wk.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[123/291] Writing tensor layers.13.attention.wv.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[124/291] Writing tensor layers.13.attention.wo.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[125/291] Writing tensor layers.13.attention_norm.weight | size 4096 | type UnquantizedDataType(name='F32')\n",
"[126/291] Writing tensor layers.13.feed_forward.w1.weight | size 11008 x 4096 | type UnquantizedDataType(name='F16')\n",
"[127/291] Writing tensor layers.13.feed_forward.w2.weight | size 4096 x 11008 | type UnquantizedDataType(name='F16')\n",
"[128/291] Writing tensor layers.13.feed_forward.w3.weight | size 11008 x 4096 | type UnquantizedDataType(name='F16')\n",
"[129/291] Writing tensor layers.13.ffn_norm.weight | size 4096 | type UnquantizedDataType(name='F32')\n",
"[130/291] Writing tensor layers.14.attention.wq.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[131/291] Writing tensor layers.14.attention.wk.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[132/291] Writing tensor layers.14.attention.wv.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[133/291] Writing tensor layers.14.attention.wo.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[134/291] Writing tensor layers.14.attention_norm.weight | size 4096 | type UnquantizedDataType(name='F32')\n",
"[135/291] Writing tensor layers.14.feed_forward.w1.weight | size 11008 x 4096 | type UnquantizedDataType(name='F16')\n",
"[136/291] Writing tensor layers.14.feed_forward.w2.weight | size 4096 x 11008 | type UnquantizedDataType(name='F16')\n",
"[137/291] Writing tensor layers.14.feed_forward.w3.weight | size 11008 x 4096 | type UnquantizedDataType(name='F16')\n",
"[138/291] Writing tensor layers.14.ffn_norm.weight | size 4096 | type UnquantizedDataType(name='F32')\n",
"[139/291] Writing tensor layers.15.attention.wq.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[140/291] Writing tensor layers.15.attention.wk.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[141/291] Writing tensor layers.15.attention.wv.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[142/291] Writing tensor layers.15.attention.wo.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[143/291] Writing tensor layers.15.attention_norm.weight | size 4096 | type UnquantizedDataType(name='F32')\n",
"[144/291] Writing tensor layers.15.feed_forward.w1.weight | size 11008 x 4096 | type UnquantizedDataType(name='F16')\n",
"[145/291] Writing tensor layers.15.feed_forward.w2.weight | size 4096 x 11008 | type UnquantizedDataType(name='F16')\n",
"[146/291] Writing tensor layers.15.feed_forward.w3.weight | size 11008 x 4096 | type UnquantizedDataType(name='F16')\n",
"[147/291] Writing tensor layers.15.ffn_norm.weight | size 4096 | type UnquantizedDataType(name='F32')\n",
"[148/291] Writing tensor layers.16.attention.wq.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[149/291] Writing tensor layers.16.attention.wk.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[150/291] Writing tensor layers.16.attention.wv.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[151/291] Writing tensor layers.16.attention.wo.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[152/291] Writing tensor layers.16.attention_norm.weight | size 4096 | type UnquantizedDataType(name='F32')\n",
"[153/291] Writing tensor layers.16.feed_forward.w1.weight | size 11008 x 4096 | type UnquantizedDataType(name='F16')\n",
"[154/291] Writing tensor layers.16.feed_forward.w2.weight | size 4096 x 11008 | type UnquantizedDataType(name='F16')\n",
"[155/291] Writing tensor layers.16.feed_forward.w3.weight | size 11008 x 4096 | type UnquantizedDataType(name='F16')\n",
"[156/291] Writing tensor layers.16.ffn_norm.weight | size 4096 | type UnquantizedDataType(name='F32')\n",
"[157/291] Writing tensor layers.17.attention.wq.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[158/291] Writing tensor layers.17.attention.wk.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[159/291] Writing tensor layers.17.attention.wv.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[160/291] Writing tensor layers.17.attention.wo.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[161/291] Writing tensor layers.17.attention_norm.weight | size 4096 | type UnquantizedDataType(name='F32')\n",
"[162/291] Writing tensor layers.17.feed_forward.w1.weight | size 11008 x 4096 | type UnquantizedDataType(name='F16')\n",
"[163/291] Writing tensor layers.17.feed_forward.w2.weight | size 4096 x 11008 | type UnquantizedDataType(name='F16')\n",
"[164/291] Writing tensor layers.17.feed_forward.w3.weight | size 11008 x 4096 | type UnquantizedDataType(name='F16')\n",
"[165/291] Writing tensor layers.17.ffn_norm.weight | size 4096 | type UnquantizedDataType(name='F32')\n",
"[166/291] Writing tensor layers.18.attention.wq.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[167/291] Writing tensor layers.18.attention.wk.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[168/291] Writing tensor layers.18.attention.wv.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[169/291] Writing tensor layers.18.attention.wo.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[170/291] Writing tensor layers.18.attention_norm.weight | size 4096 | type UnquantizedDataType(name='F32')\n",
"[171/291] Writing tensor layers.18.feed_forward.w1.weight | size 11008 x 4096 | type UnquantizedDataType(name='F16')\n",
"[172/291] Writing tensor layers.18.feed_forward.w2.weight | size 4096 x 11008 | type UnquantizedDataType(name='F16')\n",
"[173/291] Writing tensor layers.18.feed_forward.w3.weight | size 11008 x 4096 | type UnquantizedDataType(name='F16')\n",
"[174/291] Writing tensor layers.18.ffn_norm.weight | size 4096 | type UnquantizedDataType(name='F32')\n",
"[175/291] Writing tensor layers.19.attention.wq.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[176/291] Writing tensor layers.19.attention.wk.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[177/291] Writing tensor layers.19.attention.wv.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[178/291] Writing tensor layers.19.attention.wo.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[179/291] Writing tensor layers.19.attention_norm.weight | size 4096 | type UnquantizedDataType(name='F32')\n",
"[180/291] Writing tensor layers.19.feed_forward.w1.weight | size 11008 x 4096 | type UnquantizedDataType(name='F16')\n",
"[181/291] Writing tensor layers.19.feed_forward.w2.weight | size 4096 x 11008 | type UnquantizedDataType(name='F16')\n",
"[182/291] Writing tensor layers.19.feed_forward.w3.weight | size 11008 x 4096 | type UnquantizedDataType(name='F16')\n",
"[183/291] Writing tensor layers.19.ffn_norm.weight | size 4096 | type UnquantizedDataType(name='F32')\n",
"[184/291] Writing tensor layers.20.attention.wq.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[185/291] Writing tensor layers.20.attention.wk.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[186/291] Writing tensor layers.20.attention.wv.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[187/291] Writing tensor layers.20.attention.wo.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[188/291] Writing tensor layers.20.attention_norm.weight | size 4096 | type UnquantizedDataType(name='F32')\n",
"[189/291] Writing tensor layers.20.feed_forward.w1.weight | size 11008 x 4096 | type UnquantizedDataType(name='F16')\n",
"[190/291] Writing tensor layers.20.feed_forward.w2.weight | size 4096 x 11008 | type UnquantizedDataType(name='F16')\n",
"[191/291] Writing tensor layers.20.feed_forward.w3.weight | size 11008 x 4096 | type UnquantizedDataType(name='F16')\n",
"[192/291] Writing tensor layers.20.ffn_norm.weight | size 4096 | type UnquantizedDataType(name='F32')\n",
"[193/291] Writing tensor layers.21.attention.wq.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[194/291] Writing tensor layers.21.attention.wk.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[195/291] Writing tensor layers.21.attention.wv.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[196/291] Writing tensor layers.21.attention.wo.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[197/291] Writing tensor layers.21.attention_norm.weight | size 4096 | type UnquantizedDataType(name='F32')\n",
"[198/291] Writing tensor layers.21.feed_forward.w1.weight | size 11008 x 4096 | type UnquantizedDataType(name='F16')\n",
"[199/291] Writing tensor layers.21.feed_forward.w2.weight | size 4096 x 11008 | type UnquantizedDataType(name='F16')\n",
"[200/291] Writing tensor layers.21.feed_forward.w3.weight | size 11008 x 4096 | type UnquantizedDataType(name='F16')\n",
"[201/291] Writing tensor layers.21.ffn_norm.weight | size 4096 | type UnquantizedDataType(name='F32')\n",
"[202/291] Writing tensor layers.22.attention.wq.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[203/291] Writing tensor layers.22.attention.wk.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[204/291] Writing tensor layers.22.attention.wv.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[205/291] Writing tensor layers.22.attention.wo.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[206/291] Writing tensor layers.22.attention_norm.weight | size 4096 | type UnquantizedDataType(name='F32')\n",
"[207/291] Writing tensor layers.22.feed_forward.w1.weight | size 11008 x 4096 | type UnquantizedDataType(name='F16')\n",
"[208/291] Writing tensor layers.22.feed_forward.w2.weight | size 4096 x 11008 | type UnquantizedDataType(name='F16')\n",
"[209/291] Writing tensor layers.22.feed_forward.w3.weight | size 11008 x 4096 | type UnquantizedDataType(name='F16')\n",
"[210/291] Writing tensor layers.22.ffn_norm.weight | size 4096 | type UnquantizedDataType(name='F32')\n",
"[211/291] Writing tensor layers.23.attention.wq.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[212/291] Writing tensor layers.23.attention.wk.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[213/291] Writing tensor layers.23.attention.wv.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[214/291] Writing tensor layers.23.attention.wo.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[215/291] Writing tensor layers.23.attention_norm.weight | size 4096 | type UnquantizedDataType(name='F32')\n",
"[216/291] Writing tensor layers.23.feed_forward.w1.weight | size 11008 x 4096 | type UnquantizedDataType(name='F16')\n",
"[217/291] Writing tensor layers.23.feed_forward.w2.weight | size 4096 x 11008 | type UnquantizedDataType(name='F16')\n",
"[218/291] Writing tensor layers.23.feed_forward.w3.weight | size 11008 x 4096 | type UnquantizedDataType(name='F16')\n",
"[219/291] Writing tensor layers.23.ffn_norm.weight | size 4096 | type UnquantizedDataType(name='F32')\n",
"[220/291] Writing tensor layers.24.attention.wq.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[221/291] Writing tensor layers.24.attention.wk.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[222/291] Writing tensor layers.24.attention.wv.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[223/291] Writing tensor layers.24.attention.wo.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[224/291] Writing tensor layers.24.attention_norm.weight | size 4096 | type UnquantizedDataType(name='F32')\n",
"[225/291] Writing tensor layers.24.feed_forward.w1.weight | size 11008 x 4096 | type UnquantizedDataType(name='F16')\n",
"[226/291] Writing tensor layers.24.feed_forward.w2.weight | size 4096 x 11008 | type UnquantizedDataType(name='F16')\n",
"[227/291] Writing tensor layers.24.feed_forward.w3.weight | size 11008 x 4096 | type UnquantizedDataType(name='F16')\n",
"[228/291] Writing tensor layers.24.ffn_norm.weight | size 4096 | type UnquantizedDataType(name='F32')\n",
"[229/291] Writing tensor layers.25.attention.wq.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[230/291] Writing tensor layers.25.attention.wk.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[231/291] Writing tensor layers.25.attention.wv.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[232/291] Writing tensor layers.25.attention.wo.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[233/291] Writing tensor layers.25.attention_norm.weight | size 4096 | type UnquantizedDataType(name='F32')\n",
"[234/291] Writing tensor layers.25.feed_forward.w1.weight | size 11008 x 4096 | type UnquantizedDataType(name='F16')\n",
"[235/291] Writing tensor layers.25.feed_forward.w2.weight | size 4096 x 11008 | type UnquantizedDataType(name='F16')\n",
"[236/291] Writing tensor layers.25.feed_forward.w3.weight | size 11008 x 4096 | type UnquantizedDataType(name='F16')\n",
"[237/291] Writing tensor layers.25.ffn_norm.weight | size 4096 | type UnquantizedDataType(name='F32')\n",
"[238/291] Writing tensor layers.26.attention.wq.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[239/291] Writing tensor layers.26.attention.wk.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[240/291] Writing tensor layers.26.attention.wv.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[241/291] Writing tensor layers.26.attention.wo.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[242/291] Writing tensor layers.26.attention_norm.weight | size 4096 | type UnquantizedDataType(name='F32')\n",
"[243/291] Writing tensor layers.26.feed_forward.w1.weight | size 11008 x 4096 | type UnquantizedDataType(name='F16')\n",
"[244/291] Writing tensor layers.26.feed_forward.w2.weight | size 4096 x 11008 | type UnquantizedDataType(name='F16')\n",
"[245/291] Writing tensor layers.26.feed_forward.w3.weight | size 11008 x 4096 | type UnquantizedDataType(name='F16')\n",
"[246/291] Writing tensor layers.26.ffn_norm.weight | size 4096 | type UnquantizedDataType(name='F32')\n",
"[247/291] Writing tensor layers.27.attention.wq.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[248/291] Writing tensor layers.27.attention.wk.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[249/291] Writing tensor layers.27.attention.wv.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[250/291] Writing tensor layers.27.attention.wo.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[251/291] Writing tensor layers.27.attention_norm.weight | size 4096 | type UnquantizedDataType(name='F32')\n",
"[252/291] Writing tensor layers.27.feed_forward.w1.weight | size 11008 x 4096 | type UnquantizedDataType(name='F16')\n",
"[253/291] Writing tensor layers.27.feed_forward.w2.weight | size 4096 x 11008 | type UnquantizedDataType(name='F16')\n",
"[254/291] Writing tensor layers.27.feed_forward.w3.weight | size 11008 x 4096 | type UnquantizedDataType(name='F16')\n",
"[255/291] Writing tensor layers.27.ffn_norm.weight | size 4096 | type UnquantizedDataType(name='F32')\n",
"[256/291] Writing tensor layers.28.attention.wq.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[257/291] Writing tensor layers.28.attention.wk.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[258/291] Writing tensor layers.28.attention.wv.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[259/291] Writing tensor layers.28.attention.wo.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[260/291] Writing tensor layers.28.attention_norm.weight | size 4096 | type UnquantizedDataType(name='F32')\n",
"[261/291] Writing tensor layers.28.feed_forward.w1.weight | size 11008 x 4096 | type UnquantizedDataType(name='F16')\n",
"[262/291] Writing tensor layers.28.feed_forward.w2.weight | size 4096 x 11008 | type UnquantizedDataType(name='F16')\n",
"[263/291] Writing tensor layers.28.feed_forward.w3.weight | size 11008 x 4096 | type UnquantizedDataType(name='F16')\n",
"[264/291] Writing tensor layers.28.ffn_norm.weight | size 4096 | type UnquantizedDataType(name='F32')\n",
"[265/291] Writing tensor layers.29.attention.wq.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[266/291] Writing tensor layers.29.attention.wk.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[267/291] Writing tensor layers.29.attention.wv.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[268/291] Writing tensor layers.29.attention.wo.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[269/291] Writing tensor layers.29.attention_norm.weight | size 4096 | type UnquantizedDataType(name='F32')\n",
"[270/291] Writing tensor layers.29.feed_forward.w1.weight | size 11008 x 4096 | type UnquantizedDataType(name='F16')\n",
"[271/291] Writing tensor layers.29.feed_forward.w2.weight | size 4096 x 11008 | type UnquantizedDataType(name='F16')\n",
"[272/291] Writing tensor layers.29.feed_forward.w3.weight | size 11008 x 4096 | type UnquantizedDataType(name='F16')\n",
"[273/291] Writing tensor layers.29.ffn_norm.weight | size 4096 | type UnquantizedDataType(name='F32')\n",
"[274/291] Writing tensor layers.30.attention.wq.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[275/291] Writing tensor layers.30.attention.wk.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[276/291] Writing tensor layers.30.attention.wv.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[277/291] Writing tensor layers.30.attention.wo.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[278/291] Writing tensor layers.30.attention_norm.weight | size 4096 | type UnquantizedDataType(name='F32')\n",
"[279/291] Writing tensor layers.30.feed_forward.w1.weight | size 11008 x 4096 | type UnquantizedDataType(name='F16')\n",
"[280/291] Writing tensor layers.30.feed_forward.w2.weight | size 4096 x 11008 | type UnquantizedDataType(name='F16')\n",
"[281/291] Writing tensor layers.30.feed_forward.w3.weight | size 11008 x 4096 | type UnquantizedDataType(name='F16')\n",
"[282/291] Writing tensor layers.30.ffn_norm.weight | size 4096 | type UnquantizedDataType(name='F32')\n",
"[283/291] Writing tensor layers.31.attention.wq.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[284/291] Writing tensor layers.31.attention.wk.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[285/291] Writing tensor layers.31.attention.wv.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[286/291] Writing tensor layers.31.attention.wo.weight | size 4096 x 4096 | type UnquantizedDataType(name='F16')\n",
"[287/291] Writing tensor layers.31.attention_norm.weight | size 4096 | type UnquantizedDataType(name='F32')\n",
"[288/291] Writing tensor layers.31.feed_forward.w1.weight | size 11008 x 4096 | type UnquantizedDataType(name='F16')\n",
"[289/291] Writing tensor layers.31.feed_forward.w2.weight | size 4096 x 11008 | type UnquantizedDataType(name='F16')\n",
"[290/291] Writing tensor layers.31.feed_forward.w3.weight | size 11008 x 4096 | type UnquantizedDataType(name='F16')\n",
"[291/291] Writing tensor layers.31.ffn_norm.weight | size 4096 | type UnquantizedDataType(name='F32')\n",
"Wrote zh-models/7B/ggml-model-f16.bin\n"
]
}
]
},
{
"cell_type": "markdown",
"source": [
"### 将FP16模型量化为4-bit\n",
"\n",
"我们进一步将FP16模型转换为4-bit量化模型，此处选择的是新版Q4_K方法。"
],
"metadata": {
"id": "hEZEJAVYCHkc"
}
},
{
"cell_type": "code",
"source": [
"!cd llama.cpp && ./quantize ./zh-models/7B/ggml-model-f16.bin ./zh-models/7B/ggml-model-q4_K.bin q4_K"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "2xyais7OUVDI",
"outputId": "ebe6c758-15ff-4150-f68f-c5cddb1dfff6"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"main: build = 670 (254a7a7)\n",
"main: quantizing './zh-models/7B/ggml-model-f16.bin' to './zh-models/7B/ggml-model-q4_K.bin' as Q4_K\n",
"llama.cpp: loading model from ./zh-models/7B/ggml-model-f16.bin\n",
"llama.cpp: saving model to ./zh-models/7B/ggml-model-q4_K.bin\n",
"[ 1/ 291] tok_embeddings.weight - 4096 x 49954, type = f16, quantizing .. size = 390.27 MB -> 109.76 MB | hist: \n",
"[ 2/ 291] norm.weight - 4096, type = f32, size = 0.016 MB\n",
"[ 3/ 291] output.weight - 4096 x 49954, type = f16, quantizing .. size = 390.27 MB -> 160.07 MB | hist: \n",
"[ 4/ 291] layers.0.attention.wq.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 5/ 291] layers.0.attention.wk.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 6/ 291] layers.0.attention.wv.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 13.12 MB | hist: \n",
"[ 7/ 291] layers.0.attention.wo.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 8/ 291] layers.0.attention_norm.weight - 4096, type = f32, size = 0.016 MB\n",
"[ 9/ 291] layers.0.feed_forward.w1.weight - 4096 x 11008, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 10/ 291] layers.0.feed_forward.w2.weight - 11008 x 4096, type = f16, quantizing .. size = 86.00 MB -> 35.27 MB | hist: \n",
"[ 11/ 291] layers.0.feed_forward.w3.weight - 4096 x 11008, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 12/ 291] layers.0.ffn_norm.weight - 4096, type = f32, size = 0.016 MB\n",
"[ 13/ 291] layers.1.attention.wq.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 14/ 291] layers.1.attention.wk.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 15/ 291] layers.1.attention.wv.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 13.12 MB | hist: \n",
"[ 16/ 291] layers.1.attention.wo.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 17/ 291] layers.1.attention_norm.weight - 4096, type = f32, size = 0.016 MB\n",
"[ 18/ 291] layers.1.feed_forward.w1.weight - 4096 x 11008, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 19/ 291] layers.1.feed_forward.w2.weight - 11008 x 4096, type = f16, quantizing .. size = 86.00 MB -> 35.27 MB | hist: \n",
"[ 20/ 291] layers.1.feed_forward.w3.weight - 4096 x 11008, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 21/ 291] layers.1.ffn_norm.weight - 4096, type = f32, size = 0.016 MB\n",
"[ 22/ 291] layers.2.attention.wq.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 23/ 291] layers.2.attention.wk.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 24/ 291] layers.2.attention.wv.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 13.12 MB | hist: \n",
"[ 25/ 291] layers.2.attention.wo.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 26/ 291] layers.2.attention_norm.weight - 4096, type = f32, size = 0.016 MB\n",
"[ 27/ 291] layers.2.feed_forward.w1.weight - 4096 x 11008, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 28/ 291] layers.2.feed_forward.w2.weight - 11008 x 4096, type = f16, quantizing .. size = 86.00 MB -> 35.27 MB | hist: \n",
"[ 29/ 291] layers.2.feed_forward.w3.weight - 4096 x 11008, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 30/ 291] layers.2.ffn_norm.weight - 4096, type = f32, size = 0.016 MB\n",
"[ 31/ 291] layers.3.attention.wq.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 32/ 291] layers.3.attention.wk.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 33/ 291] layers.3.attention.wv.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 13.12 MB | hist: \n",
"[ 34/ 291] layers.3.attention.wo.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 35/ 291] layers.3.attention_norm.weight - 4096, type = f32, size = 0.016 MB\n",
"[ 36/ 291] layers.3.feed_forward.w1.weight - 4096 x 11008, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 37/ 291] layers.3.feed_forward.w2.weight - 11008 x 4096, type = f16, quantizing .. size = 86.00 MB -> 35.27 MB | hist: \n",
"[ 38/ 291] layers.3.feed_forward.w3.weight - 4096 x 11008, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 39/ 291] layers.3.ffn_norm.weight - 4096, type = f32, size = 0.016 MB\n",
"[ 40/ 291] layers.4.attention.wq.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 41/ 291] layers.4.attention.wk.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 42/ 291] layers.4.attention.wv.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 43/ 291] layers.4.attention.wo.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 44/ 291] layers.4.attention_norm.weight - 4096, type = f32, size = 0.016 MB\n",
"[ 45/ 291] layers.4.feed_forward.w1.weight - 4096 x 11008, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 46/ 291] layers.4.feed_forward.w2.weight - 11008 x 4096, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 47/ 291] layers.4.feed_forward.w3.weight - 4096 x 11008, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 48/ 291] layers.4.ffn_norm.weight - 4096, type = f32, size = 0.016 MB\n",
"[ 49/ 291] layers.5.attention.wq.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 50/ 291] layers.5.attention.wk.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 51/ 291] layers.5.attention.wv.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 52/ 291] layers.5.attention.wo.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 53/ 291] layers.5.attention_norm.weight - 4096, type = f32, size = 0.016 MB\n",
"[ 54/ 291] layers.5.feed_forward.w1.weight - 4096 x 11008, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 55/ 291] layers.5.feed_forward.w2.weight - 11008 x 4096, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 56/ 291] layers.5.feed_forward.w3.weight - 4096 x 11008, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 57/ 291] layers.5.ffn_norm.weight - 4096, type = f32, size = 0.016 MB\n",
"[ 58/ 291] layers.6.attention.wq.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 59/ 291] layers.6.attention.wk.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 60/ 291] layers.6.attention.wv.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 13.12 MB | hist: \n",
"[ 61/ 291] layers.6.attention.wo.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 62/ 291] layers.6.attention_norm.weight - 4096, type = f32, size = 0.016 MB\n",
"[ 63/ 291] layers.6.feed_forward.w1.weight - 4096 x 11008, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 64/ 291] layers.6.feed_forward.w2.weight - 11008 x 4096, type = f16, quantizing .. size = 86.00 MB -> 35.27 MB | hist: \n",
"[ 65/ 291] layers.6.feed_forward.w3.weight - 4096 x 11008, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 66/ 291] layers.6.ffn_norm.weight - 4096, type = f32, size = 0.016 MB\n",
"[ 67/ 291] layers.7.attention.wq.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 68/ 291] layers.7.attention.wk.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 69/ 291] layers.7.attention.wv.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 70/ 291] layers.7.attention.wo.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 71/ 291] layers.7.attention_norm.weight - 4096, type = f32, size = 0.016 MB\n",
"[ 72/ 291] layers.7.feed_forward.w1.weight - 4096 x 11008, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 73/ 291] layers.7.feed_forward.w2.weight - 11008 x 4096, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 74/ 291] layers.7.feed_forward.w3.weight - 4096 x 11008, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 75/ 291] layers.7.ffn_norm.weight - 4096, type = f32, size = 0.016 MB\n",
"[ 76/ 291] layers.8.attention.wq.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 77/ 291] layers.8.attention.wk.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 78/ 291] layers.8.attention.wv.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 79/ 291] layers.8.attention.wo.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 80/ 291] layers.8.attention_norm.weight - 4096, type = f32, size = 0.016 MB\n",
"[ 81/ 291] layers.8.feed_forward.w1.weight - 4096 x 11008, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 82/ 291] layers.8.feed_forward.w2.weight - 11008 x 4096, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 83/ 291] layers.8.feed_forward.w3.weight - 4096 x 11008, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 84/ 291] layers.8.ffn_norm.weight - 4096, type = f32, size = 0.016 MB\n",
"[ 85/ 291] layers.9.attention.wq.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 86/ 291] layers.9.attention.wk.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 87/ 291] layers.9.attention.wv.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 13.12 MB | hist: \n",
"[ 88/ 291] layers.9.attention.wo.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 89/ 291] layers.9.attention_norm.weight - 4096, type = f32, size = 0.016 MB\n",
"[ 90/ 291] layers.9.feed_forward.w1.weight - 4096 x 11008, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 91/ 291] layers.9.feed_forward.w2.weight - 11008 x 4096, type = f16, quantizing .. size = 86.00 MB -> 35.27 MB | hist: \n",
"[ 92/ 291] layers.9.feed_forward.w3.weight - 4096 x 11008, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 93/ 291] layers.9.ffn_norm.weight - 4096, type = f32, size = 0.016 MB\n",
"[ 94/ 291] layers.10.attention.wq.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 95/ 291] layers.10.attention.wk.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 96/ 291] layers.10.attention.wv.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 97/ 291] layers.10.attention.wo.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 98/ 291] layers.10.attention_norm.weight - 4096, type = f32, size = 0.016 MB\n",
"[ 99/ 291] layers.10.feed_forward.w1.weight - 4096 x 11008, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 100/ 291] layers.10.feed_forward.w2.weight - 11008 x 4096, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 101/ 291] layers.10.feed_forward.w3.weight - 4096 x 11008, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 102/ 291] layers.10.ffn_norm.weight - 4096, type = f32, size = 0.016 MB\n",
"[ 103/ 291] layers.11.attention.wq.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 104/ 291] layers.11.attention.wk.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 105/ 291] layers.11.attention.wv.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 106/ 291] layers.11.attention.wo.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 107/ 291] layers.11.attention_norm.weight - 4096, type = f32, size = 0.016 MB\n",
"[ 108/ 291] layers.11.feed_forward.w1.weight - 4096 x 11008, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 109/ 291] layers.11.feed_forward.w2.weight - 11008 x 4096, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 110/ 291] layers.11.feed_forward.w3.weight - 4096 x 11008, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 111/ 291] layers.11.ffn_norm.weight - 4096, type = f32, size = 0.016 MB\n",
"[ 112/ 291] layers.12.attention.wq.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 113/ 291] layers.12.attention.wk.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 114/ 291] layers.12.attention.wv.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 13.12 MB | hist: \n",
"[ 115/ 291] layers.12.attention.wo.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 116/ 291] layers.12.attention_norm.weight - 4096, type = f32, size = 0.016 MB\n",
"[ 117/ 291] layers.12.feed_forward.w1.weight - 4096 x 11008, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 118/ 291] layers.12.feed_forward.w2.weight - 11008 x 4096, type = f16, quantizing .. size = 86.00 MB -> 35.27 MB | hist: \n",
"[ 119/ 291] layers.12.feed_forward.w3.weight - 4096 x 11008, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 120/ 291] layers.12.ffn_norm.weight - 4096, type = f32, size = 0.016 MB\n",
"[ 121/ 291] layers.13.attention.wq.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 122/ 291] layers.13.attention.wk.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 123/ 291] layers.13.attention.wv.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 124/ 291] layers.13.attention.wo.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 125/ 291] layers.13.attention_norm.weight - 4096, type = f32, size = 0.016 MB\n",
"[ 126/ 291] layers.13.feed_forward.w1.weight - 4096 x 11008, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 127/ 291] layers.13.feed_forward.w2.weight - 11008 x 4096, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 128/ 291] layers.13.feed_forward.w3.weight - 4096 x 11008, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 129/ 291] layers.13.ffn_norm.weight - 4096, type = f32, size = 0.016 MB\n",
"[ 130/ 291] layers.14.attention.wq.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 131/ 291] layers.14.attention.wk.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 132/ 291] layers.14.attention.wv.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 133/ 291] layers.14.attention.wo.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 134/ 291] layers.14.attention_norm.weight - 4096, type = f32, size = 0.016 MB\n",
"[ 135/ 291] layers.14.feed_forward.w1.weight - 4096 x 11008, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 136/ 291] layers.14.feed_forward.w2.weight - 11008 x 4096, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 137/ 291] layers.14.feed_forward.w3.weight - 4096 x 11008, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 138/ 291] layers.14.ffn_norm.weight - 4096, type = f32, size = 0.016 MB\n",
"[ 139/ 291] layers.15.attention.wq.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 140/ 291] layers.15.attention.wk.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 141/ 291] layers.15.attention.wv.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 13.12 MB | hist: \n",
"[ 142/ 291] layers.15.attention.wo.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 143/ 291] layers.15.attention_norm.weight - 4096, type = f32, size = 0.016 MB\n",
"[ 144/ 291] layers.15.feed_forward.w1.weight - 4096 x 11008, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 145/ 291] layers.15.feed_forward.w2.weight - 11008 x 4096, type = f16, quantizing .. size = 86.00 MB -> 35.27 MB | hist: \n",
"[ 146/ 291] layers.15.feed_forward.w3.weight - 4096 x 11008, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 147/ 291] layers.15.ffn_norm.weight - 4096, type = f32, size = 0.016 MB\n",
"[ 148/ 291] layers.16.attention.wq.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 149/ 291] layers.16.attention.wk.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 150/ 291] layers.16.attention.wv.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 151/ 291] layers.16.attention.wo.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 152/ 291] layers.16.attention_norm.weight - 4096, type = f32, size = 0.016 MB\n",
"[ 153/ 291] layers.16.feed_forward.w1.weight - 4096 x 11008, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 154/ 291] layers.16.feed_forward.w2.weight - 11008 x 4096, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 155/ 291] layers.16.feed_forward.w3.weight - 4096 x 11008, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 156/ 291] layers.16.ffn_norm.weight - 4096, type = f32, size = 0.016 MB\n",
"[ 157/ 291] layers.17.attention.wq.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 158/ 291] layers.17.attention.wk.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 159/ 291] layers.17.attention.wv.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 160/ 291] layers.17.attention.wo.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 161/ 291] layers.17.attention_norm.weight - 4096, type = f32, size = 0.016 MB\n",
"[ 162/ 291] layers.17.feed_forward.w1.weight - 4096 x 11008, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 163/ 291] layers.17.feed_forward.w2.weight - 11008 x 4096, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 164/ 291] layers.17.feed_forward.w3.weight - 4096 x 11008, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 165/ 291] layers.17.ffn_norm.weight - 4096, type = f32, size = 0.016 MB\n",
"[ 166/ 291] layers.18.attention.wq.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 167/ 291] layers.18.attention.wk.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 168/ 291] layers.18.attention.wv.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 13.12 MB | hist: \n",
"[ 169/ 291] layers.18.attention.wo.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 170/ 291] layers.18.attention_norm.weight - 4096, type = f32, size = 0.016 MB\n",
"[ 171/ 291] layers.18.feed_forward.w1.weight - 4096 x 11008, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 172/ 291] layers.18.feed_forward.w2.weight - 11008 x 4096, type = f16, quantizing .. size = 86.00 MB -> 35.27 MB | hist: \n",
"[ 173/ 291] layers.18.feed_forward.w3.weight - 4096 x 11008, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 174/ 291] layers.18.ffn_norm.weight - 4096, type = f32, size = 0.016 MB\n",
"[ 175/ 291] layers.19.attention.wq.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 176/ 291] layers.19.attention.wk.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 177/ 291] layers.19.attention.wv.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 178/ 291] layers.19.attention.wo.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 179/ 291] layers.19.attention_norm.weight - 4096, type = f32, size = 0.016 MB\n",
"[ 180/ 291] layers.19.feed_forward.w1.weight - 4096 x 11008, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 181/ 291] layers.19.feed_forward.w2.weight - 11008 x 4096, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 182/ 291] layers.19.feed_forward.w3.weight - 4096 x 11008, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 183/ 291] layers.19.ffn_norm.weight - 4096, type = f32, size = 0.016 MB\n",
"[ 184/ 291] layers.20.attention.wq.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 185/ 291] layers.20.attention.wk.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 186/ 291] layers.20.attention.wv.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 187/ 291] layers.20.attention.wo.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 188/ 291] layers.20.attention_norm.weight - 4096, type = f32, size = 0.016 MB\n",
"[ 189/ 291] layers.20.feed_forward.w1.weight - 4096 x 11008, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 190/ 291] layers.20.feed_forward.w2.weight - 11008 x 4096, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 191/ 291] layers.20.feed_forward.w3.weight - 4096 x 11008, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 192/ 291] layers.20.ffn_norm.weight - 4096, type = f32, size = 0.016 MB\n",
"[ 193/ 291] layers.21.attention.wq.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 194/ 291] layers.21.attention.wk.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 195/ 291] layers.21.attention.wv.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 13.12 MB | hist: \n",
"[ 196/ 291] layers.21.attention.wo.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 197/ 291] layers.21.attention_norm.weight - 4096, type = f32, size = 0.016 MB\n",
"[ 198/ 291] layers.21.feed_forward.w1.weight - 4096 x 11008, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 199/ 291] layers.21.feed_forward.w2.weight - 11008 x 4096, type = f16, quantizing .. size = 86.00 MB -> 35.27 MB | hist: \n",
"[ 200/ 291] layers.21.feed_forward.w3.weight - 4096 x 11008, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 201/ 291] layers.21.ffn_norm.weight - 4096, type = f32, size = 0.016 MB\n",
"[ 202/ 291] layers.22.attention.wq.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 203/ 291] layers.22.attention.wk.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 204/ 291] layers.22.attention.wv.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 205/ 291] layers.22.attention.wo.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 206/ 291] layers.22.attention_norm.weight - 4096, type = f32, size = 0.016 MB\n",
"[ 207/ 291] layers.22.feed_forward.w1.weight - 4096 x 11008, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 208/ 291] layers.22.feed_forward.w2.weight - 11008 x 4096, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 209/ 291] layers.22.feed_forward.w3.weight - 4096 x 11008, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 210/ 291] layers.22.ffn_norm.weight - 4096, type = f32, size = 0.016 MB\n",
"[ 211/ 291] layers.23.attention.wq.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 212/ 291] layers.23.attention.wk.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 213/ 291] layers.23.attention.wv.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 214/ 291] layers.23.attention.wo.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 215/ 291] layers.23.attention_norm.weight - 4096, type = f32, size = 0.016 MB\n",
"[ 216/ 291] layers.23.feed_forward.w1.weight - 4096 x 11008, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 217/ 291] layers.23.feed_forward.w2.weight - 11008 x 4096, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 218/ 291] layers.23.feed_forward.w3.weight - 4096 x 11008, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 219/ 291] layers.23.ffn_norm.weight - 4096, type = f32, size = 0.016 MB\n",
"[ 220/ 291] layers.24.attention.wq.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 221/ 291] layers.24.attention.wk.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 222/ 291] layers.24.attention.wv.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 13.12 MB | hist: \n",
"[ 223/ 291] layers.24.attention.wo.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 224/ 291] layers.24.attention_norm.weight - 4096, type = f32, size = 0.016 MB\n",
"[ 225/ 291] layers.24.feed_forward.w1.weight - 4096 x 11008, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 226/ 291] layers.24.feed_forward.w2.weight - 11008 x 4096, type = f16, quantizing .. size = 86.00 MB -> 35.27 MB | hist: \n",
"[ 227/ 291] layers.24.feed_forward.w3.weight - 4096 x 11008, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 228/ 291] layers.24.ffn_norm.weight - 4096, type = f32, size = 0.016 MB\n",
"[ 229/ 291] layers.25.attention.wq.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 230/ 291] layers.25.attention.wk.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 231/ 291] layers.25.attention.wv.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 232/ 291] layers.25.attention.wo.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 233/ 291] layers.25.attention_norm.weight - 4096, type = f32, size = 0.016 MB\n",
"[ 234/ 291] layers.25.feed_forward.w1.weight - 4096 x 11008, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 235/ 291] layers.25.feed_forward.w2.weight - 11008 x 4096, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 236/ 291] layers.25.feed_forward.w3.weight - 4096 x 11008, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 237/ 291] layers.25.ffn_norm.weight - 4096, type = f32, size = 0.016 MB\n",
"[ 238/ 291] layers.26.attention.wq.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 239/ 291] layers.26.attention.wk.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 240/ 291] layers.26.attention.wv.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 241/ 291] layers.26.attention.wo.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 242/ 291] layers.26.attention_norm.weight - 4096, type = f32, size = 0.016 MB\n",
"[ 243/ 291] layers.26.feed_forward.w1.weight - 4096 x 11008, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 244/ 291] layers.26.feed_forward.w2.weight - 11008 x 4096, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 245/ 291] layers.26.feed_forward.w3.weight - 4096 x 11008, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 246/ 291] layers.26.ffn_norm.weight - 4096, type = f32, size = 0.016 MB\n",
"[ 247/ 291] layers.27.attention.wq.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 248/ 291] layers.27.attention.wk.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 249/ 291] layers.27.attention.wv.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 13.12 MB | hist: \n",
"[ 250/ 291] layers.27.attention.wo.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 251/ 291] layers.27.attention_norm.weight - 4096, type = f32, size = 0.016 MB\n",
"[ 252/ 291] layers.27.feed_forward.w1.weight - 4096 x 11008, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 253/ 291] layers.27.feed_forward.w2.weight - 11008 x 4096, type = f16, quantizing .. size = 86.00 MB -> 35.27 MB | hist: \n",
"[ 254/ 291] layers.27.feed_forward.w3.weight - 4096 x 11008, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 255/ 291] layers.27.ffn_norm.weight - 4096, type = f32, size = 0.016 MB\n",
"[ 256/ 291] layers.28.attention.wq.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 257/ 291] layers.28.attention.wk.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 258/ 291] layers.28.attention.wv.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 13.12 MB | hist: \n",
"[ 259/ 291] layers.28.attention.wo.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 260/ 291] layers.28.attention_norm.weight - 4096, type = f32, size = 0.016 MB\n",
"[ 261/ 291] layers.28.feed_forward.w1.weight - 4096 x 11008, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 262/ 291] layers.28.feed_forward.w2.weight - 11008 x 4096, type = f16, quantizing .. size = 86.00 MB -> 35.27 MB | hist: \n",
"[ 263/ 291] layers.28.feed_forward.w3.weight - 4096 x 11008, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 264/ 291] layers.28.ffn_norm.weight - 4096, type = f32, size = 0.016 MB\n",
"[ 265/ 291] layers.29.attention.wq.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 266/ 291] layers.29.attention.wk.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 267/ 291] layers.29.attention.wv.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 13.12 MB | hist: \n",
"[ 268/ 291] layers.29.attention.wo.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 269/ 291] layers.29.attention_norm.weight - 4096, type = f32, size = 0.016 MB\n",
"[ 270/ 291] layers.29.feed_forward.w1.weight - 4096 x 11008, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 271/ 291] layers.29.feed_forward.w2.weight - 11008 x 4096, type = f16, quantizing .. size = 86.00 MB -> 35.27 MB | hist: \n",
"[ 272/ 291] layers.29.feed_forward.w3.weight - 4096 x 11008, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 273/ 291] layers.29.ffn_norm.weight - 4096, type = f32, size = 0.016 MB\n",
"[ 274/ 291] layers.30.attention.wq.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 275/ 291] layers.30.attention.wk.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 276/ 291] layers.30.attention.wv.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 13.12 MB | hist: \n",
"[ 277/ 291] layers.30.attention.wo.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 278/ 291] layers.30.attention_norm.weight - 4096, type = f32, size = 0.016 MB\n",
"[ 279/ 291] layers.30.feed_forward.w1.weight - 4096 x 11008, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 280/ 291] layers.30.feed_forward.w2.weight - 11008 x 4096, type = f16, quantizing .. size = 86.00 MB -> 35.27 MB | hist: \n",
"[ 281/ 291] layers.30.feed_forward.w3.weight - 4096 x 11008, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 282/ 291] layers.30.ffn_norm.weight - 4096, type = f32, size = 0.016 MB\n",
"[ 283/ 291] layers.31.attention.wq.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 284/ 291] layers.31.attention.wk.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 285/ 291] layers.31.attention.wv.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 13.12 MB | hist: \n",
"[ 286/ 291] layers.31.attention.wo.weight - 4096 x 4096, type = f16, quantizing .. size = 32.00 MB -> 9.00 MB | hist: \n",
"[ 287/ 291] layers.31.attention_norm.weight - 4096, type = f32, size = 0.016 MB\n",
"[ 288/ 291] layers.31.feed_forward.w1.weight - 4096 x 11008, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 289/ 291] layers.31.feed_forward.w2.weight - 11008 x 4096, type = f16, quantizing .. size = 86.00 MB -> 35.27 MB | hist: \n",
"[ 290/ 291] layers.31.feed_forward.w3.weight - 4096 x 11008, type = f16, quantizing .. size = 86.00 MB -> 24.19 MB | hist: \n",
"[ 291/ 291] layers.31.ffn_norm.weight - 4096, type = f32, size = 0.016 MB\n",
"llama_model_quantize_internal: model size = 13133.55 MB\n",
"llama_model_quantize_internal: quant size = 3988.22 MB\n",
"\n",
"main: quantize time = 153421.48 ms\n",
"main: total time = 153421.48 ms\n"
]
}
]
},
{
"cell_type": "markdown",
"source": [
"### （可选）测试量化模型解码\n",
"至此已完成了所有转换步骤。\n",
"我们运行一条命令测试一下是否能够正常加载并进行对话。\n",
"\n",
"FP16和Q4量化文件存放在./llama.cpp/zh-models/7B下，可按需下载使用。"
],
"metadata": {
"id": "DLkuRAo9Vkb1"
}
},
{
"cell_type": "code",
"source": [
"!cd llama.cpp && ./main -m ./zh-models/7B/ggml-model-q4_K.bin --color -p \"详细介绍一下北京的名胜古迹：\" -n 128"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "tW-ep1BsVQtG",
"outputId": "03f0343f-3b7c-490e-a0ab-6724d79c5dc8"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"main: build = 670 (254a7a7)\n",
"main: seed = 1686819449\n",
"llama.cpp: loading model from ./zh-models/7B/ggml-model-q4_K.bin\n",
"llama_model_load_internal: format = ggjt v3 (latest)\n",
"llama_model_load_internal: n_vocab = 49954\n",
"llama_model_load_internal: n_ctx = 512\n",
"llama_model_load_internal: n_embd = 4096\n",
"llama_model_load_internal: n_mult = 256\n",
"llama_model_load_internal: n_head = 32\n",
"llama_model_load_internal: n_layer = 32\n",
"llama_model_load_internal: n_rot = 128\n",
"llama_model_load_internal: ftype = 15 (mostly Q4_K - Medium)\n",
"llama_model_load_internal: n_ff = 11008\n",
"llama_model_load_internal: n_parts = 1\n",
"llama_model_load_internal: model size = 7B\n",
"llama_model_load_internal: ggml ctx size = 0.07 MB\n",
"llama_model_load_internal: mem required = 5780.29 MB (+ 1026.00 MB per state)\n",
"................................................................................................\n",
"llama_init_from_file: kv self size = 256.00 MB\n",
"\n",
"system_info: n_threads = 4 / 4 | AVX = 1 | AVX2 = 1 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | FMA = 1 | NEON = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 0 | SSE3 = 1 | VSX = 0 | \n",
"sampling: repeat_last_n = 64, repeat_penalty = 1.100000, presence_penalty = 0.000000, frequency_penalty = 0.000000, top_k = 40, tfs_z = 1.000000, top_p = 0.950000, typical_p = 1.000000, temp = 0.800000, mirostat = 0, mirostat_lr = 0.100000, mirostat_ent = 5.000000\n",
"generate: n_ctx = 512, n_batch = 512, n_predict = 128, n_keep = 0\n",
"\n",
"\n",
"\u001b[33m 详细介绍一下北京的名胜古迹：\u001b[0m天安门、故宫、颐和园、圆明园、北海公园等。 参观后你一定会爱上这座城市！ [end of text]\n",
"\n",
"llama_print_timings: load time = 16410.24 ms\n",
"llama_print_timings: sample time = 30.04 ms / 30 runs ( 1.00 ms per token)\n",
"llama_print_timings: prompt eval time = 3479.21 ms / 11 tokens ( 316.29 ms per token)\n",
"llama_print_timings: eval time = 10516.40 ms / 29 runs ( 362.63 ms per token)\n",
"llama_print_timings: total time = 14042.46 ms\n"
]
}
]
}
]
}
Reference in New Issue View Git Blame Copy Permalink