Files
ymcui--chinese-llama-alpaca/notebooks/legacy/convert_and_quantize_chinese_llama.ipynb
T
2026-07-13 13:27:00 +08:00

1874 lines
193 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"
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
},
"language_info": {
"name": "python"
},
"gpuClass": "standard",
"accelerator": "TPU"
},
"cells": [
{
"cell_type": "markdown",
"source": [
"# 转换并量化中文LLaMA/Alpaca模型\n",
"\n",
"🎉🎉🎉 **新:现在免费用户也有机会能够转换7B和13B模型了!**\n",
"\n",
"💡 提示和小窍门:\n",
"- 免费用户默认的内存只有12G左右,**笔者用免费账号实测选择TPU的话有机会随机出35G内存**,建议多试几次。如果能随机出25G内存以上的机器就可以了转换7B模型了,35G内存以上机器就能转换13B模型了\n",
"- Pro(+)用户请选择 “代码执行程序” -> “更改运行时类型” -> “高RAM”\n",
"- 实测:转换7B级别模型,25G内存的机器就够了;转换13B级别模型需要30G以上的内存(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“高级”类型GPU\n",
"\n",
"以下信息配置信息供参考(Pro订阅下测试),运行时规格设置为“高RAM”时的设备配置如下(有随机性):\n",
"\n",
"| 硬件加速器 | RAM | 硬盘 |\n",
"| :-- | :--: | :--: |\n",
"| None | 25GB | 225GB |\n",
"| TPU | 35GB | 225GB |\n",
"| GPU(标准,T4| 25GB | 166GB |\n",
"| GPU(高性能,V100| 25GB | 166GB |\n",
"| GPU(高性能,A100| **80GB** | 166GB |\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": 1,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "E5WKFJXIL6ZU",
"outputId": "7ce317e5-c105-49a8-d1af-70c29e6246e1"
},
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n",
"Collecting transformers\n",
" Downloading transformers-4.28.0-py3-none-any.whl (7.0 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m7.0/7.0 MB\u001b[0m \u001b[31m54.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: requests in /usr/local/lib/python3.9/dist-packages (from transformers) (2.27.1)\n",
"Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.9/dist-packages (from transformers) (1.24.2)\n",
"Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.9/dist-packages (from transformers) (6.0)\n",
"Requirement already satisfied: tqdm>=4.27 in /usr/local/lib/python3.9/dist-packages (from transformers) (4.65.0)\n",
"Collecting huggingface-hub<1.0,>=0.11.0\n",
" Downloading huggingface_hub-0.13.4-py3-none-any.whl (200 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m200.1/200.1 kB\u001b[0m \u001b[31m24.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.9/dist-packages (from transformers) (2022.10.31)\n",
"Requirement already satisfied: filelock in /usr/local/lib/python3.9/dist-packages (from transformers) (3.11.0)\n",
"Collecting tokenizers!=0.11.3,<0.14,>=0.11.1\n",
" Downloading tokenizers-0.13.3-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (7.8 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m7.8/7.8 MB\u001b[0m \u001b[31m97.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.9/dist-packages (from transformers) (23.0)\n",
"Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.9/dist-packages (from huggingface-hub<1.0,>=0.11.0->transformers) (4.5.0)\n",
"Requirement already satisfied: charset-normalizer~=2.0.0 in /usr/local/lib/python3.9/dist-packages (from requests->transformers) (2.0.12)\n",
"Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.9/dist-packages (from requests->transformers) (2022.12.7)\n",
"Requirement already satisfied: urllib3<1.27,>=1.21.1 in /usr/local/lib/python3.9/dist-packages (from requests->transformers) (1.26.15)\n",
"Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.9/dist-packages (from requests->transformers) (3.4)\n",
"Installing collected packages: tokenizers, huggingface-hub, transformers\n",
"Successfully installed huggingface-hub-0.13.4 tokenizers-0.13.3 transformers-4.28.0\n",
"Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n",
"Collecting peft\n",
" Downloading peft-0.2.0-py3-none-any.whl (40 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m40.3/40.3 kB\u001b[0m \u001b[31m3.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: psutil in /usr/local/lib/python3.9/dist-packages (from peft) (5.9.4)\n",
"Requirement already satisfied: transformers in /usr/local/lib/python3.9/dist-packages (from peft) (4.28.0)\n",
"Requirement already satisfied: pyyaml in /usr/local/lib/python3.9/dist-packages (from peft) (6.0)\n",
"Requirement already satisfied: torch>=1.13.0 in /usr/local/lib/python3.9/dist-packages (from peft) (2.0.0+cu118)\n",
"Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.9/dist-packages (from peft) (23.0)\n",
"Collecting accelerate\n",
" Downloading accelerate-0.18.0-py3-none-any.whl (215 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m215.3/215.3 kB\u001b[0m \u001b[31m6.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.9/dist-packages (from peft) (1.24.2)\n",
"Requirement already satisfied: sympy in /usr/local/lib/python3.9/dist-packages (from torch>=1.13.0->peft) (1.11.1)\n",
"Requirement already satisfied: jinja2 in /usr/local/lib/python3.9/dist-packages (from torch>=1.13.0->peft) (3.1.2)\n",
"Requirement already satisfied: triton==2.0.0 in /usr/local/lib/python3.9/dist-packages (from torch>=1.13.0->peft) (2.0.0)\n",
"Requirement already satisfied: networkx in /usr/local/lib/python3.9/dist-packages (from torch>=1.13.0->peft) (3.1)\n",
"Requirement already satisfied: filelock in /usr/local/lib/python3.9/dist-packages (from torch>=1.13.0->peft) (3.11.0)\n",
"Requirement already satisfied: typing-extensions in /usr/local/lib/python3.9/dist-packages (from torch>=1.13.0->peft) (4.5.0)\n",
"Requirement already satisfied: lit in /usr/local/lib/python3.9/dist-packages (from triton==2.0.0->torch>=1.13.0->peft) (16.0.1)\n",
"Requirement already satisfied: cmake in /usr/local/lib/python3.9/dist-packages (from triton==2.0.0->torch>=1.13.0->peft) (3.25.2)\n",
"Requirement already satisfied: huggingface-hub<1.0,>=0.11.0 in /usr/local/lib/python3.9/dist-packages (from transformers->peft) (0.13.4)\n",
"Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.9/dist-packages (from transformers->peft) (2022.10.31)\n",
"Requirement already satisfied: requests in /usr/local/lib/python3.9/dist-packages (from transformers->peft) (2.27.1)\n",
"Requirement already satisfied: tokenizers!=0.11.3,<0.14,>=0.11.1 in /usr/local/lib/python3.9/dist-packages (from transformers->peft) (0.13.3)\n",
"Requirement already satisfied: tqdm>=4.27 in /usr/local/lib/python3.9/dist-packages (from transformers->peft) (4.65.0)\n",
"Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.9/dist-packages (from jinja2->torch>=1.13.0->peft) (2.1.2)\n",
"Requirement already satisfied: charset-normalizer~=2.0.0 in /usr/local/lib/python3.9/dist-packages (from requests->transformers->peft) (2.0.12)\n",
"Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.9/dist-packages (from requests->transformers->peft) (3.4)\n",
"Requirement already satisfied: urllib3<1.27,>=1.21.1 in /usr/local/lib/python3.9/dist-packages (from requests->transformers->peft) (1.26.15)\n",
"Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.9/dist-packages (from requests->transformers->peft) (2022.12.7)\n",
"Requirement already satisfied: mpmath>=0.19 in /usr/local/lib/python3.9/dist-packages (from sympy->torch>=1.13.0->peft) (1.3.0)\n",
"Installing collected packages: accelerate, peft\n",
"Successfully installed accelerate-0.18.0 peft-0.2.0\n",
"Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n",
"Collecting sentencepiece\n",
" Downloading sentencepiece-0.1.98-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.3 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.3/1.3 MB\u001b[0m \u001b[31m18.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hInstalling collected packages: sentencepiece\n",
"Successfully installed sentencepiece-0.1.98\n"
]
}
],
"source": [
"!pip install transformers\n",
"!pip install peft\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": "91a0e4ff-af63-4f8e-ab82-ee4ddf583033"
},
"execution_count": 2,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Cloning into 'Chinese-LLaMA-Alpaca'...\n",
"remote: Enumerating objects: 559, done.\u001b[K\n",
"remote: Counting objects: 100% (129/129), done.\u001b[K\n",
"remote: Compressing objects: 100% (115/115), done.\u001b[K\n",
"remote: Total 559 (delta 30), reused 22 (delta 14), pack-reused 430\u001b[K\n",
"Receiving objects: 100% (559/559), 10.71 MiB | 25.49 MiB/s, done.\n",
"Resolving deltas: 100% (333/333), done.\n",
"Cloning into 'llama.cpp'...\n",
"remote: Enumerating objects: 1701, done.\u001b[K\n",
"remote: Counting objects: 100% (1701/1701), done.\u001b[K\n",
"remote: Compressing objects: 100% (620/620), done.\u001b[K\n",
"remote: Total 1701 (delta 1084), reused 1623 (delta 1047), pack-reused 0\u001b[K\n",
"Receiving objects: 100% (1701/1701), 1.86 MiB | 14.74 MiB/s, done.\n",
"Resolving deltas: 100% (1084/1084), done.\n"
]
}
]
},
{
"cell_type": "markdown",
"source": [
"## 合并模型(以Alpaca-7B为例)\n",
"\n",
"**⚠️ 再次提醒:7B模型需要25G内存,13B模型需要35G+内存。**\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",
"\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:`decapoda-research/llama-7b-hf` *use at your own risk*\n",
"- LoRA模型:`ziqingyang/chinese-alpaca-lora-7b`\n",
"\n",
"💡 转换13B模型提示:\n",
"- 请将参数`--base_model`和`--lora_model`中的的`7b`改为`13b`即可\n",
"- **免费用户必须增加一个参数`--offload_dir`以缓解内存压力**,例如`--offload_dir ./offload_temp`\n",
"\n",
"该过程比较耗时(下载+转换),需要几分钟到十几分钟不等,请耐心等待。\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。"
],
"metadata": {
"id": "nIyxX0DSNsgQ"
}
},
{
"cell_type": "code",
"source": [
"!python ./Chinese-LLaMA-Alpaca/scripts/merge_llama_with_chinese_lora.py \\\n",
" --base_model 'decapoda-research/llama-7b-hf' \\\n",
" --lora_model 'ziqingyang/chinese-alpaca-lora-7b' \\\n",
" --output_dir alpaca-combined"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "5AV4EW5hNhVV",
"outputId": "e34419d4-b7c9-4e22-af37-abf80d4163ba"
},
"execution_count": 3,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"2023-04-14 10:13:45.382526: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT\n",
"Downloading tokenizer.model: 100% 758k/758k [00:00<00:00, 12.7MB/s]\n",
"Downloading (…)cial_tokens_map.json: 100% 96.0/96.0 [00:00<00:00, 15.3kB/s]\n",
"Downloading (…)okenizer_config.json: 100% 166/166 [00:00<00:00, 63.2kB/s]\n",
"Downloading (…)lve/main/config.json: 100% 427/427 [00:00<00:00, 63.4kB/s]\n",
"Downloading (…)model.bin.index.json: 100% 25.5k/25.5k [00:00<00:00, 9.41MB/s]\n",
"Downloading shards: 0% 0/33 [00:00<?, ?it/s]\n",
"Downloading (…)l-00001-of-00033.bin: 0% 0.00/405M [00:00<?, ?B/s]\u001b[A\n",
"Downloading (…)l-00001-of-00033.bin: 3% 10.5M/405M [00:00<00:04, 95.1MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00033.bin: 8% 31.5M/405M [00:00<00:02, 155MB/s] \u001b[A\n",
"Downloading (…)l-00001-of-00033.bin: 16% 62.9M/405M [00:00<00:01, 185MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00033.bin: 23% 94.4M/405M [00:00<00:01, 197MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00033.bin: 31% 126M/405M [00:00<00:01, 205MB/s] \u001b[A\n",
"Downloading (…)l-00001-of-00033.bin: 39% 157M/405M [00:00<00:01, 208MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00033.bin: 47% 189M/405M [00:00<00:01, 210MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00033.bin: 54% 220M/405M [00:01<00:00, 213MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00033.bin: 62% 252M/405M [00:01<00:00, 214MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00033.bin: 70% 283M/405M [00:01<00:00, 215MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00033.bin: 78% 315M/405M [00:01<00:00, 216MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00033.bin: 85% 346M/405M [00:01<00:00, 216MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00033.bin: 93% 377M/405M [00:01<00:00, 214MB/s]\u001b[A\n",
"Downloading (…)l-00001-of-00033.bin: 100% 405M/405M [00:01<00:00, 205MB/s]\n",
"Downloading shards: 3% 1/33 [00:02<01:07, 2.11s/it]\n",
"Downloading (…)l-00002-of-00033.bin: 0% 0.00/405M [00:00<?, ?B/s]\u001b[A\n",
"Downloading (…)l-00002-of-00033.bin: 3% 10.5M/405M [00:00<00:04, 91.8MB/s]\u001b[A\n",
"Downloading (…)l-00002-of-00033.bin: 8% 31.5M/405M [00:00<00:02, 150MB/s] \u001b[A\n",
"Downloading (…)l-00002-of-00033.bin: 13% 52.4M/405M [00:00<00:02, 173MB/s]\u001b[A\n",
"Downloading (…)l-00002-of-00033.bin: 18% 73.4M/405M [00:00<00:01, 182MB/s]\u001b[A\n",
"Downloading (…)l-00002-of-00033.bin: 23% 94.4M/405M [00:00<00:01, 186MB/s]\u001b[A\n",
"Downloading (…)l-00002-of-00033.bin: 28% 115M/405M [00:00<00:01, 192MB/s] \u001b[A\n",
"Downloading (…)l-00002-of-00033.bin: 34% 136M/405M [00:00<00:01, 196MB/s]\u001b[A\n",
"Downloading (…)l-00002-of-00033.bin: 39% 157M/405M [00:00<00:01, 199MB/s]\u001b[A\n",
"Downloading (…)l-00002-of-00033.bin: 44% 178M/405M [00:00<00:01, 200MB/s]\u001b[A\n",
"Downloading (…)l-00002-of-00033.bin: 49% 199M/405M [00:01<00:01, 201MB/s]\u001b[A\n",
"Downloading (…)l-00002-of-00033.bin: 54% 220M/405M [00:01<00:00, 202MB/s]\u001b[A\n",
"Downloading (…)l-00002-of-00033.bin: 60% 241M/405M [00:01<00:00, 201MB/s]\u001b[A\n",
"Downloading (…)l-00002-of-00033.bin: 65% 262M/405M [00:01<00:00, 202MB/s]\u001b[A\n",
"Downloading (…)l-00002-of-00033.bin: 70% 283M/405M [00:01<00:00, 203MB/s]\u001b[A\n",
"Downloading (…)l-00002-of-00033.bin: 75% 304M/405M [00:01<00:00, 203MB/s]\u001b[A\n",
"Downloading (…)l-00002-of-00033.bin: 80% 325M/405M [00:01<00:00, 203MB/s]\u001b[A\n",
"Downloading (…)l-00002-of-00033.bin: 85% 346M/405M [00:01<00:00, 198MB/s]\u001b[A\n",
"Downloading (…)l-00002-of-00033.bin: 91% 367M/405M [00:01<00:00, 200MB/s]\u001b[A\n",
"Downloading (…)l-00002-of-00033.bin: 100% 405M/405M [00:02<00:00, 194MB/s]\n",
"Downloading shards: 6% 2/33 [00:04<01:07, 2.17s/it]\n",
"Downloading (…)l-00003-of-00033.bin: 0% 0.00/405M [00:00<?, ?B/s]\u001b[A\n",
"Downloading (…)l-00003-of-00033.bin: 3% 10.5M/405M [00:00<00:04, 90.9MB/s]\u001b[A\n",
"Downloading (…)l-00003-of-00033.bin: 8% 31.5M/405M [00:00<00:02, 143MB/s] \u001b[A\n",
"Downloading (…)l-00003-of-00033.bin: 13% 52.4M/405M [00:00<00:02, 166MB/s]\u001b[A\n",
"Downloading (…)l-00003-of-00033.bin: 18% 73.4M/405M [00:00<00:01, 179MB/s]\u001b[A\n",
"Downloading (…)l-00003-of-00033.bin: 23% 94.4M/405M [00:00<00:01, 187MB/s]\u001b[A\n",
"Downloading (…)l-00003-of-00033.bin: 28% 115M/405M [00:00<00:01, 190MB/s] \u001b[A\n",
"Downloading (…)l-00003-of-00033.bin: 34% 136M/405M [00:00<00:01, 192MB/s]\u001b[A\n",
"Downloading (…)l-00003-of-00033.bin: 39% 157M/405M [00:00<00:01, 194MB/s]\u001b[A\n",
"Downloading (…)l-00003-of-00033.bin: 44% 178M/405M [00:00<00:01, 196MB/s]\u001b[A\n",
"Downloading (…)l-00003-of-00033.bin: 49% 199M/405M [00:01<00:01, 197MB/s]\u001b[A\n",
"Downloading (…)l-00003-of-00033.bin: 54% 220M/405M [00:01<00:00, 197MB/s]\u001b[A\n",
"Downloading (…)l-00003-of-00033.bin: 60% 241M/405M [00:01<00:00, 198MB/s]\u001b[A\n",
"Downloading (…)l-00003-of-00033.bin: 65% 262M/405M [00:01<00:00, 199MB/s]\u001b[A\n",
"Downloading (…)l-00003-of-00033.bin: 70% 283M/405M [00:01<00:00, 199MB/s]\u001b[A\n",
"Downloading (…)l-00003-of-00033.bin: 75% 304M/405M [00:01<00:00, 200MB/s]\u001b[A\n",
"Downloading (…)l-00003-of-00033.bin: 80% 325M/405M [00:01<00:00, 200MB/s]\u001b[A\n",
"Downloading (…)l-00003-of-00033.bin: 85% 346M/405M [00:01<00:00, 200MB/s]\u001b[A\n",
"Downloading (…)l-00003-of-00033.bin: 91% 367M/405M [00:01<00:00, 200MB/s]\u001b[A\n",
"Downloading (…)l-00003-of-00033.bin: 100% 405M/405M [00:02<00:00, 187MB/s]\n",
"Downloading shards: 9% 3/33 [00:06<01:06, 2.23s/it]\n",
"Downloading (…)l-00004-of-00033.bin: 0% 0.00/405M [00:00<?, ?B/s]\u001b[A\n",
"Downloading (…)l-00004-of-00033.bin: 3% 10.5M/405M [00:00<00:04, 93.5MB/s]\u001b[A\n",
"Downloading (…)l-00004-of-00033.bin: 8% 31.5M/405M [00:00<00:02, 152MB/s] \u001b[A\n",
"Downloading (…)l-00004-of-00033.bin: 13% 52.4M/405M [00:00<00:02, 175MB/s]\u001b[A\n",
"Downloading (…)l-00004-of-00033.bin: 18% 73.4M/405M [00:00<00:01, 182MB/s]\u001b[A\n",
"Downloading (…)l-00004-of-00033.bin: 23% 94.4M/405M [00:00<00:01, 190MB/s]\u001b[A\n",
"Downloading (…)l-00004-of-00033.bin: 28% 115M/405M [00:00<00:01, 195MB/s] \u001b[A\n",
"Downloading (…)l-00004-of-00033.bin: 34% 136M/405M [00:00<00:01, 198MB/s]\u001b[A\n",
"Downloading (…)l-00004-of-00033.bin: 39% 157M/405M [00:00<00:01, 200MB/s]\u001b[A\n",
"Downloading (…)l-00004-of-00033.bin: 44% 178M/405M [00:00<00:01, 201MB/s]\u001b[A\n",
"Downloading (…)l-00004-of-00033.bin: 49% 199M/405M [00:01<00:01, 203MB/s]\u001b[A\n",
"Downloading (…)l-00004-of-00033.bin: 54% 220M/405M [00:01<00:00, 204MB/s]\u001b[A\n",
"Downloading (…)l-00004-of-00033.bin: 60% 241M/405M [00:01<00:00, 204MB/s]\u001b[A\n",
"Downloading (…)l-00004-of-00033.bin: 65% 262M/405M [00:01<00:00, 201MB/s]\u001b[A\n",
"Downloading (…)l-00004-of-00033.bin: 70% 283M/405M [00:01<00:00, 202MB/s]\u001b[A\n",
"Downloading (…)l-00004-of-00033.bin: 75% 304M/405M [00:01<00:00, 203MB/s]\u001b[A\n",
"Downloading (…)l-00004-of-00033.bin: 80% 325M/405M [00:01<00:00, 204MB/s]\u001b[A\n",
"Downloading (…)l-00004-of-00033.bin: 85% 346M/405M [00:01<00:00, 201MB/s]\u001b[A\n",
"Downloading (…)l-00004-of-00033.bin: 91% 367M/405M [00:01<00:00, 200MB/s]\u001b[A\n",
"Downloading (…)l-00004-of-00033.bin: 100% 405M/405M [00:02<00:00, 195MB/s]\n",
"Downloading shards: 12% 4/33 [00:08<01:04, 2.22s/it]\n",
"Downloading (…)l-00005-of-00033.bin: 0% 0.00/405M [00:00<?, ?B/s]\u001b[A\n",
"Downloading (…)l-00005-of-00033.bin: 3% 10.5M/405M [00:00<00:04, 86.5MB/s]\u001b[A\n",
"Downloading (…)l-00005-of-00033.bin: 8% 31.5M/405M [00:00<00:02, 144MB/s] \u001b[A\n",
"Downloading (…)l-00005-of-00033.bin: 13% 52.4M/405M [00:00<00:02, 167MB/s]\u001b[A\n",
"Downloading (…)l-00005-of-00033.bin: 18% 73.4M/405M [00:00<00:01, 178MB/s]\u001b[A\n",
"Downloading (…)l-00005-of-00033.bin: 23% 94.4M/405M [00:00<00:01, 185MB/s]\u001b[A\n",
"Downloading (…)l-00005-of-00033.bin: 28% 115M/405M [00:00<00:01, 189MB/s] \u001b[A\n",
"Downloading (…)l-00005-of-00033.bin: 34% 136M/405M [00:00<00:01, 187MB/s]\u001b[A\n",
"Downloading (…)l-00005-of-00033.bin: 39% 157M/405M [00:00<00:01, 190MB/s]\u001b[A\n",
"Downloading (…)l-00005-of-00033.bin: 44% 178M/405M [00:00<00:01, 192MB/s]\u001b[A\n",
"Downloading (…)l-00005-of-00033.bin: 49% 199M/405M [00:01<00:01, 193MB/s]\u001b[A\n",
"Downloading (…)l-00005-of-00033.bin: 54% 220M/405M [00:01<00:00, 192MB/s]\u001b[A\n",
"Downloading (…)l-00005-of-00033.bin: 60% 241M/405M [00:01<00:00, 192MB/s]\u001b[A\n",
"Downloading (…)l-00005-of-00033.bin: 65% 262M/405M [00:01<00:00, 193MB/s]\u001b[A\n",
"Downloading (…)l-00005-of-00033.bin: 70% 283M/405M [00:01<00:00, 195MB/s]\u001b[A\n",
"Downloading (…)l-00005-of-00033.bin: 75% 304M/405M [00:01<00:00, 195MB/s]\u001b[A\n",
"Downloading (…)l-00005-of-00033.bin: 80% 325M/405M [00:01<00:00, 196MB/s]\u001b[A\n",
"Downloading (…)l-00005-of-00033.bin: 85% 346M/405M [00:01<00:00, 196MB/s]\u001b[A\n",
"Downloading (…)l-00005-of-00033.bin: 91% 367M/405M [00:01<00:00, 197MB/s]\u001b[A\n",
"Downloading (…)l-00005-of-00033.bin: 100% 405M/405M [00:02<00:00, 188MB/s]\n",
"Downloading shards: 15% 5/33 [00:11<01:03, 2.26s/it]\n",
"Downloading (…)l-00006-of-00033.bin: 0% 0.00/405M [00:00<?, ?B/s]\u001b[A\n",
"Downloading (…)l-00006-of-00033.bin: 3% 10.5M/405M [00:00<00:04, 90.3MB/s]\u001b[A\n",
"Downloading (…)l-00006-of-00033.bin: 8% 31.5M/405M [00:00<00:02, 150MB/s] \u001b[A\n",
"Downloading (…)l-00006-of-00033.bin: 13% 52.4M/405M [00:00<00:02, 173MB/s]\u001b[A\n",
"Downloading (…)l-00006-of-00033.bin: 18% 73.4M/405M [00:00<00:01, 182MB/s]\u001b[A\n",
"Downloading (…)l-00006-of-00033.bin: 23% 94.4M/405M [00:00<00:01, 186MB/s]\u001b[A\n",
"Downloading (…)l-00006-of-00033.bin: 28% 115M/405M [00:00<00:01, 190MB/s] \u001b[A\n",
"Downloading (…)l-00006-of-00033.bin: 34% 136M/405M [00:00<00:01, 194MB/s]\u001b[A\n",
"Downloading (…)l-00006-of-00033.bin: 39% 157M/405M [00:00<00:01, 196MB/s]\u001b[A\n",
"Downloading (…)l-00006-of-00033.bin: 44% 178M/405M [00:00<00:01, 194MB/s]\u001b[A\n",
"Downloading (…)l-00006-of-00033.bin: 49% 199M/405M [00:01<00:01, 196MB/s]\u001b[A\n",
"Downloading (…)l-00006-of-00033.bin: 54% 220M/405M [00:01<00:00, 197MB/s]\u001b[A\n",
"Downloading (…)l-00006-of-00033.bin: 60% 241M/405M [00:01<00:00, 198MB/s]\u001b[A\n",
"Downloading (…)l-00006-of-00033.bin: 65% 262M/405M [00:01<00:00, 199MB/s]\u001b[A\n",
"Downloading (…)l-00006-of-00033.bin: 70% 283M/405M [00:01<00:00, 200MB/s]\u001b[A\n",
"Downloading (…)l-00006-of-00033.bin: 75% 304M/405M [00:01<00:00, 201MB/s]\u001b[A\n",
"Downloading (…)l-00006-of-00033.bin: 80% 325M/405M [00:01<00:00, 201MB/s]\u001b[A\n",
"Downloading (…)l-00006-of-00033.bin: 85% 346M/405M [00:01<00:00, 198MB/s]\u001b[A\n",
"Downloading (…)l-00006-of-00033.bin: 91% 367M/405M [00:01<00:00, 191MB/s]\u001b[A\n",
"Downloading (…)l-00006-of-00033.bin: 100% 405M/405M [00:02<00:00, 190MB/s]\n",
"Downloading shards: 18% 6/33 [00:13<01:01, 2.26s/it]\n",
"Downloading (…)l-00007-of-00033.bin: 0% 0.00/405M [00:00<?, ?B/s]\u001b[A\n",
"Downloading (…)l-00007-of-00033.bin: 3% 10.5M/405M [00:00<00:04, 93.4MB/s]\u001b[A\n",
"Downloading (…)l-00007-of-00033.bin: 8% 31.5M/405M [00:00<00:02, 152MB/s] \u001b[A\n",
"Downloading (…)l-00007-of-00033.bin: 13% 52.4M/405M [00:00<00:02, 176MB/s]\u001b[A\n",
"Downloading (…)l-00007-of-00033.bin: 18% 73.4M/405M [00:00<00:01, 188MB/s]\u001b[A\n",
"Downloading (…)l-00007-of-00033.bin: 23% 94.4M/405M [00:00<00:01, 195MB/s]\u001b[A\n",
"Downloading (…)l-00007-of-00033.bin: 28% 115M/405M [00:00<00:01, 198MB/s] \u001b[A\n",
"Downloading (…)l-00007-of-00033.bin: 34% 136M/405M [00:00<00:01, 201MB/s]\u001b[A\n",
"Downloading (…)l-00007-of-00033.bin: 39% 157M/405M [00:00<00:01, 203MB/s]\u001b[A\n",
"Downloading (…)l-00007-of-00033.bin: 44% 178M/405M [00:00<00:01, 204MB/s]\u001b[A\n",
"Downloading (…)l-00007-of-00033.bin: 49% 199M/405M [00:01<00:01, 205MB/s]\u001b[A\n",
"Downloading (…)l-00007-of-00033.bin: 54% 220M/405M [00:01<00:00, 203MB/s]\u001b[A\n",
"Downloading (…)l-00007-of-00033.bin: 60% 241M/405M [00:01<00:00, 200MB/s]\u001b[A\n",
"Downloading (…)l-00007-of-00033.bin: 65% 262M/405M [00:01<00:00, 203MB/s]\u001b[A\n",
"Downloading (…)l-00007-of-00033.bin: 70% 283M/405M [00:01<00:00, 204MB/s]\u001b[A\n",
"Downloading (…)l-00007-of-00033.bin: 75% 304M/405M [00:01<00:00, 204MB/s]\u001b[A\n",
"Downloading (…)l-00007-of-00033.bin: 80% 325M/405M [00:01<00:00, 206MB/s]\u001b[A\n",
"Downloading (…)l-00007-of-00033.bin: 85% 346M/405M [00:01<00:00, 206MB/s]\u001b[A\n",
"Downloading (…)l-00007-of-00033.bin: 91% 367M/405M [00:01<00:00, 206MB/s]\u001b[A\n",
"Downloading (…)l-00007-of-00033.bin: 100% 405M/405M [00:02<00:00, 197MB/s]\n",
"Downloading shards: 21% 7/33 [00:15<00:58, 2.24s/it]\n",
"Downloading (…)l-00008-of-00033.bin: 0% 0.00/405M [00:00<?, ?B/s]\u001b[A\n",
"Downloading (…)l-00008-of-00033.bin: 3% 10.5M/405M [00:00<00:04, 93.4MB/s]\u001b[A\n",
"Downloading (…)l-00008-of-00033.bin: 8% 31.5M/405M [00:00<00:02, 153MB/s] \u001b[A\n",
"Downloading (…)l-00008-of-00033.bin: 13% 52.4M/405M [00:00<00:01, 177MB/s]\u001b[A\n",
"Downloading (…)l-00008-of-00033.bin: 18% 73.4M/405M [00:00<00:01, 188MB/s]\u001b[A\n",
"Downloading (…)l-00008-of-00033.bin: 23% 94.4M/405M [00:00<00:01, 195MB/s]\u001b[A\n",
"Downloading (…)l-00008-of-00033.bin: 28% 115M/405M [00:00<00:01, 199MB/s] \u001b[A\n",
"Downloading (…)l-00008-of-00033.bin: 34% 136M/405M [00:00<00:01, 202MB/s]\u001b[A\n",
"Downloading (…)l-00008-of-00033.bin: 39% 157M/405M [00:00<00:01, 203MB/s]\u001b[A\n",
"Downloading (…)l-00008-of-00033.bin: 44% 178M/405M [00:00<00:01, 204MB/s]\u001b[A\n",
"Downloading (…)l-00008-of-00033.bin: 49% 199M/405M [00:01<00:01, 201MB/s]\u001b[A\n",
"Downloading (…)l-00008-of-00033.bin: 54% 220M/405M [00:01<00:00, 200MB/s]\u001b[A\n",
"Downloading (…)l-00008-of-00033.bin: 60% 241M/405M [00:01<00:00, 201MB/s]\u001b[A\n",
"Downloading (…)l-00008-of-00033.bin: 65% 262M/405M [00:01<00:00, 202MB/s]\u001b[A\n",
"Downloading (…)l-00008-of-00033.bin: 70% 283M/405M [00:01<00:00, 203MB/s]\u001b[A\n",
"Downloading (…)l-00008-of-00033.bin: 75% 304M/405M [00:01<00:00, 204MB/s]\u001b[A\n",
"Downloading (…)l-00008-of-00033.bin: 80% 325M/405M [00:01<00:00, 205MB/s]\u001b[A\n",
"Downloading (…)l-00008-of-00033.bin: 85% 346M/405M [00:01<00:00, 206MB/s]\u001b[A\n",
"Downloading (…)l-00008-of-00033.bin: 91% 367M/405M [00:01<00:00, 206MB/s]\u001b[A\n",
"Downloading (…)l-00008-of-00033.bin: 100% 405M/405M [00:02<00:00, 197MB/s]\n",
"Downloading shards: 24% 8/33 [00:17<00:55, 2.22s/it]\n",
"Downloading (…)l-00009-of-00033.bin: 0% 0.00/405M [00:00<?, ?B/s]\u001b[A\n",
"Downloading (…)l-00009-of-00033.bin: 3% 10.5M/405M [00:00<00:04, 89.5MB/s]\u001b[A\n",
"Downloading (…)l-00009-of-00033.bin: 8% 31.5M/405M [00:00<00:02, 149MB/s] \u001b[A\n",
"Downloading (…)l-00009-of-00033.bin: 13% 52.4M/405M [00:00<00:02, 173MB/s]\u001b[A\n",
"Downloading (…)l-00009-of-00033.bin: 18% 73.4M/405M [00:00<00:01, 182MB/s]\u001b[A\n",
"Downloading (…)l-00009-of-00033.bin: 23% 94.4M/405M [00:00<00:01, 189MB/s]\u001b[A\n",
"Downloading (…)l-00009-of-00033.bin: 28% 115M/405M [00:00<00:01, 195MB/s] \u001b[A\n",
"Downloading (…)l-00009-of-00033.bin: 34% 136M/405M [00:00<00:01, 198MB/s]\u001b[A\n",
"Downloading (…)l-00009-of-00033.bin: 39% 157M/405M [00:00<00:01, 200MB/s]\u001b[A\n",
"Downloading (…)l-00009-of-00033.bin: 44% 178M/405M [00:00<00:01, 201MB/s]\u001b[A\n",
"Downloading (…)l-00009-of-00033.bin: 49% 199M/405M [00:01<00:01, 202MB/s]\u001b[A\n",
"Downloading (…)l-00009-of-00033.bin: 54% 220M/405M [00:01<00:00, 203MB/s]\u001b[A\n",
"Downloading (…)l-00009-of-00033.bin: 60% 241M/405M [00:01<00:00, 201MB/s]\u001b[A\n",
"Downloading (…)l-00009-of-00033.bin: 65% 262M/405M [00:01<00:00, 200MB/s]\u001b[A\n",
"Downloading (…)l-00009-of-00033.bin: 70% 283M/405M [00:01<00:00, 202MB/s]\u001b[A\n",
"Downloading (…)l-00009-of-00033.bin: 75% 304M/405M [00:01<00:00, 203MB/s]\u001b[A\n",
"Downloading (…)l-00009-of-00033.bin: 80% 325M/405M [00:01<00:00, 204MB/s]\u001b[A\n",
"Downloading (…)l-00009-of-00033.bin: 85% 346M/405M [00:01<00:00, 200MB/s]\u001b[A\n",
"Downloading (…)l-00009-of-00033.bin: 91% 367M/405M [00:01<00:00, 200MB/s]\u001b[A\n",
"Downloading (…)l-00009-of-00033.bin: 100% 405M/405M [00:02<00:00, 194MB/s]\n",
"Downloading shards: 27% 9/33 [00:20<00:53, 2.22s/it]\n",
"Downloading (…)l-00010-of-00033.bin: 0% 0.00/405M [00:00<?, ?B/s]\u001b[A\n",
"Downloading (…)l-00010-of-00033.bin: 3% 10.5M/405M [00:00<00:04, 93.7MB/s]\u001b[A\n",
"Downloading (…)l-00010-of-00033.bin: 8% 31.5M/405M [00:00<00:02, 152MB/s] \u001b[A\n",
"Downloading (…)l-00010-of-00033.bin: 13% 52.4M/405M [00:00<00:02, 175MB/s]\u001b[A\n",
"Downloading (…)l-00010-of-00033.bin: 18% 73.4M/405M [00:00<00:01, 186MB/s]\u001b[A\n",
"Downloading (…)l-00010-of-00033.bin: 23% 94.4M/405M [00:00<00:01, 193MB/s]\u001b[A\n",
"Downloading (…)l-00010-of-00033.bin: 28% 115M/405M [00:00<00:01, 196MB/s] \u001b[A\n",
"Downloading (…)l-00010-of-00033.bin: 34% 136M/405M [00:00<00:01, 195MB/s]\u001b[A\n",
"Downloading (…)l-00010-of-00033.bin: 39% 157M/405M [00:00<00:01, 198MB/s]\u001b[A\n",
"Downloading (…)l-00010-of-00033.bin: 44% 178M/405M [00:00<00:01, 200MB/s]\u001b[A\n",
"Downloading (…)l-00010-of-00033.bin: 52% 210M/405M [00:01<00:00, 204MB/s]\u001b[A\n",
"Downloading (…)l-00010-of-00033.bin: 57% 231M/405M [00:01<00:00, 204MB/s]\u001b[A\n",
"Downloading (…)l-00010-of-00033.bin: 62% 252M/405M [00:01<00:00, 204MB/s]\u001b[A\n",
"Downloading (…)l-00010-of-00033.bin: 67% 273M/405M [00:01<00:00, 205MB/s]\u001b[A\n",
"Downloading (…)l-00010-of-00033.bin: 73% 294M/405M [00:01<00:00, 205MB/s]\u001b[A\n",
"Downloading (…)l-00010-of-00033.bin: 78% 315M/405M [00:01<00:00, 205MB/s]\u001b[A\n",
"Downloading (…)l-00010-of-00033.bin: 83% 336M/405M [00:01<00:00, 205MB/s]\u001b[A\n",
"Downloading (…)l-00010-of-00033.bin: 88% 357M/405M [00:01<00:00, 205MB/s]\u001b[A\n",
"Downloading (…)l-00010-of-00033.bin: 93% 377M/405M [00:01<00:00, 205MB/s]\u001b[A\n",
"Downloading (…)l-00010-of-00033.bin: 100% 405M/405M [00:02<00:00, 196MB/s]\n",
"Downloading shards: 30% 10/33 [00:22<00:50, 2.22s/it]\n",
"Downloading (…)l-00011-of-00033.bin: 0% 0.00/405M [00:00<?, ?B/s]\u001b[A\n",
"Downloading (…)l-00011-of-00033.bin: 3% 10.5M/405M [00:00<00:04, 92.9MB/s]\u001b[A\n",
"Downloading (…)l-00011-of-00033.bin: 8% 31.5M/405M [00:00<00:02, 149MB/s] \u001b[A\n",
"Downloading (…)l-00011-of-00033.bin: 13% 52.4M/405M [00:00<00:02, 173MB/s]\u001b[A\n",
"Downloading (…)l-00011-of-00033.bin: 18% 73.4M/405M [00:00<00:01, 183MB/s]\u001b[A\n",
"Downloading (…)l-00011-of-00033.bin: 23% 94.4M/405M [00:00<00:01, 189MB/s]\u001b[A\n",
"Downloading (…)l-00011-of-00033.bin: 28% 115M/405M [00:00<00:01, 195MB/s] \u001b[A\n",
"Downloading (…)l-00011-of-00033.bin: 34% 136M/405M [00:00<00:01, 198MB/s]\u001b[A\n",
"Downloading (…)l-00011-of-00033.bin: 39% 157M/405M [00:00<00:01, 200MB/s]\u001b[A\n",
"Downloading (…)l-00011-of-00033.bin: 44% 178M/405M [00:00<00:01, 202MB/s]\u001b[A\n",
"Downloading (…)l-00011-of-00033.bin: 49% 199M/405M [00:01<00:01, 203MB/s]\u001b[A\n",
"Downloading (…)l-00011-of-00033.bin: 54% 220M/405M [00:01<00:00, 204MB/s]\u001b[A\n",
"Downloading (…)l-00011-of-00033.bin: 60% 241M/405M [00:01<00:00, 204MB/s]\u001b[A\n",
"Downloading (…)l-00011-of-00033.bin: 65% 262M/405M [00:01<00:00, 202MB/s]\u001b[A\n",
"Downloading (…)l-00011-of-00033.bin: 70% 283M/405M [00:01<00:00, 203MB/s]\u001b[A\n",
"Downloading (…)l-00011-of-00033.bin: 75% 304M/405M [00:01<00:00, 203MB/s]\u001b[A\n",
"Downloading (…)l-00011-of-00033.bin: 80% 325M/405M [00:01<00:00, 204MB/s]\u001b[A\n",
"Downloading (…)l-00011-of-00033.bin: 85% 346M/405M [00:01<00:00, 203MB/s]\u001b[A\n",
"Downloading (…)l-00011-of-00033.bin: 91% 367M/405M [00:01<00:00, 200MB/s]\u001b[A\n",
"Downloading (…)l-00011-of-00033.bin: 100% 405M/405M [00:02<00:00, 195MB/s]\n",
"Downloading shards: 33% 11/33 [00:24<00:48, 2.21s/it]\n",
"Downloading (…)l-00012-of-00033.bin: 0% 0.00/405M [00:00<?, ?B/s]\u001b[A\n",
"Downloading (…)l-00012-of-00033.bin: 3% 10.5M/405M [00:00<00:04, 86.7MB/s]\u001b[A\n",
"Downloading (…)l-00012-of-00033.bin: 8% 31.5M/405M [00:00<00:02, 143MB/s] \u001b[A\n",
"Downloading (…)l-00012-of-00033.bin: 13% 52.4M/405M [00:00<00:02, 165MB/s]\u001b[A\n",
"Downloading (…)l-00012-of-00033.bin: 18% 73.4M/405M [00:00<00:01, 177MB/s]\u001b[A\n",
"Downloading (…)l-00012-of-00033.bin: 23% 94.4M/405M [00:00<00:01, 185MB/s]\u001b[A\n",
"Downloading (…)l-00012-of-00033.bin: 28% 115M/405M [00:00<00:01, 189MB/s] \u001b[A\n",
"Downloading (…)l-00012-of-00033.bin: 34% 136M/405M [00:00<00:01, 187MB/s]\u001b[A\n",
"Downloading (…)l-00012-of-00033.bin: 39% 157M/405M [00:00<00:01, 190MB/s]\u001b[A\n",
"Downloading (…)l-00012-of-00033.bin: 44% 178M/405M [00:00<00:01, 192MB/s]\u001b[A\n",
"Downloading (…)l-00012-of-00033.bin: 49% 199M/405M [00:01<00:01, 193MB/s]\u001b[A\n",
"Downloading (…)l-00012-of-00033.bin: 54% 220M/405M [00:01<00:00, 192MB/s]\u001b[A\n",
"Downloading (…)l-00012-of-00033.bin: 60% 241M/405M [00:01<00:00, 191MB/s]\u001b[A\n",
"Downloading (…)l-00012-of-00033.bin: 65% 262M/405M [00:01<00:00, 191MB/s]\u001b[A\n",
"Downloading (…)l-00012-of-00033.bin: 70% 283M/405M [00:01<00:00, 192MB/s]\u001b[A\n",
"Downloading (…)l-00012-of-00033.bin: 75% 304M/405M [00:01<00:00, 193MB/s]\u001b[A\n",
"Downloading (…)l-00012-of-00033.bin: 80% 325M/405M [00:01<00:00, 193MB/s]\u001b[A\n",
"Downloading (…)l-00012-of-00033.bin: 85% 346M/405M [00:01<00:00, 194MB/s]\u001b[A\n",
"Downloading (…)l-00012-of-00033.bin: 91% 367M/405M [00:01<00:00, 194MB/s]\u001b[A\n",
"Downloading (…)l-00012-of-00033.bin: 100% 405M/405M [00:02<00:00, 186MB/s]\n",
"Downloading shards: 36% 12/33 [00:26<00:47, 2.25s/it]\n",
"Downloading (…)l-00013-of-00033.bin: 0% 0.00/405M [00:00<?, ?B/s]\u001b[A\n",
"Downloading (…)l-00013-of-00033.bin: 3% 10.5M/405M [00:00<00:04, 92.5MB/s]\u001b[A\n",
"Downloading (…)l-00013-of-00033.bin: 8% 31.5M/405M [00:00<00:02, 151MB/s] \u001b[A\n",
"Downloading (…)l-00013-of-00033.bin: 13% 52.4M/405M [00:00<00:02, 175MB/s]\u001b[A\n",
"Downloading (…)l-00013-of-00033.bin: 18% 73.4M/405M [00:00<00:01, 187MB/s]\u001b[A\n",
"Downloading (…)l-00013-of-00033.bin: 23% 94.4M/405M [00:00<00:01, 193MB/s]\u001b[A\n",
"Downloading (…)l-00013-of-00033.bin: 28% 115M/405M [00:00<00:01, 197MB/s] \u001b[A\n",
"Downloading (…)l-00013-of-00033.bin: 34% 136M/405M [00:00<00:01, 198MB/s]\u001b[A\n",
"Downloading (…)l-00013-of-00033.bin: 39% 157M/405M [00:00<00:01, 196MB/s]\u001b[A\n",
"Downloading (…)l-00013-of-00033.bin: 44% 178M/405M [00:00<00:01, 196MB/s]\u001b[A\n",
"Downloading (…)l-00013-of-00033.bin: 49% 199M/405M [00:01<00:01, 198MB/s]\u001b[A\n",
"Downloading (…)l-00013-of-00033.bin: 54% 220M/405M [00:01<00:00, 200MB/s]\u001b[A\n",
"Downloading (…)l-00013-of-00033.bin: 60% 241M/405M [00:01<00:00, 200MB/s]\u001b[A\n",
"Downloading (…)l-00013-of-00033.bin: 65% 262M/405M [00:01<00:00, 202MB/s]\u001b[A\n",
"Downloading (…)l-00013-of-00033.bin: 70% 283M/405M [00:01<00:00, 203MB/s]\u001b[A\n",
"Downloading (…)l-00013-of-00033.bin: 75% 304M/405M [00:01<00:00, 204MB/s]\u001b[A\n",
"Downloading (…)l-00013-of-00033.bin: 80% 325M/405M [00:01<00:00, 203MB/s]\u001b[A\n",
"Downloading (…)l-00013-of-00033.bin: 85% 346M/405M [00:01<00:00, 202MB/s]\u001b[A\n",
"Downloading (…)l-00013-of-00033.bin: 91% 367M/405M [00:01<00:00, 203MB/s]\u001b[A\n",
"Downloading (…)l-00013-of-00033.bin: 100% 405M/405M [00:02<00:00, 195MB/s]\n",
"Downloading shards: 39% 13/33 [00:28<00:44, 2.23s/it]\n",
"Downloading (…)l-00014-of-00033.bin: 0% 0.00/405M [00:00<?, ?B/s]\u001b[A\n",
"Downloading (…)l-00014-of-00033.bin: 3% 10.5M/405M [00:02<01:50, 3.56MB/s]\u001b[A\n",
"Downloading (…)l-00014-of-00033.bin: 5% 21.0M/405M [00:04<01:10, 5.46MB/s]\u001b[A\n",
"Downloading (…)l-00014-of-00033.bin: 8% 31.5M/405M [00:04<00:50, 7.45MB/s]\u001b[A\n",
"Downloading (…)l-00014-of-00033.bin: 10% 41.9M/405M [00:05<00:37, 9.67MB/s]\u001b[A\n",
"Downloading (…)l-00014-of-00033.bin: 13% 52.4M/405M [00:06<00:29, 12.1MB/s]\u001b[A\n",
"Downloading (…)l-00014-of-00033.bin: 16% 62.9M/405M [00:06<00:22, 14.9MB/s]\u001b[A\n",
"Downloading (…)l-00014-of-00033.bin: 18% 73.4M/405M [00:06<00:18, 17.6MB/s]\u001b[A\n",
"Downloading (…)l-00014-of-00033.bin: 21% 83.9M/405M [00:07<00:16, 20.0MB/s]\u001b[A\n",
"Downloading (…)l-00014-of-00033.bin: 23% 94.4M/405M [00:07<00:14, 21.9MB/s]\u001b[A\n",
"Downloading (…)l-00014-of-00033.bin: 26% 105M/405M [00:07<00:12, 23.5MB/s] \u001b[A\n",
"Downloading (…)l-00014-of-00033.bin: 28% 115M/405M [00:08<00:11, 24.7MB/s]\u001b[A\n",
"Downloading (…)l-00014-of-00033.bin: 31% 126M/405M [00:08<00:10, 25.6MB/s]\u001b[A\n",
"Downloading (…)l-00014-of-00033.bin: 34% 136M/405M [00:09<00:10, 26.3MB/s]\u001b[A\n",
"Downloading (…)l-00014-of-00033.bin: 36% 147M/405M [00:09<00:09, 26.8MB/s]\u001b[A\n",
"Downloading (…)l-00014-of-00033.bin: 39% 157M/405M [00:09<00:09, 27.1MB/s]\u001b[A\n",
"Downloading (…)l-00014-of-00033.bin: 41% 168M/405M [00:10<00:08, 27.4MB/s]\u001b[A\n",
"Downloading (…)l-00014-of-00033.bin: 44% 178M/405M [00:10<00:08, 27.6MB/s]\u001b[A\n",
"Downloading (…)l-00014-of-00033.bin: 47% 189M/405M [00:10<00:07, 27.7MB/s]\u001b[A\n",
"Downloading (…)l-00014-of-00033.bin: 49% 199M/405M [00:11<00:07, 27.8MB/s]\u001b[A\n",
"Downloading (…)l-00014-of-00033.bin: 52% 210M/405M [00:11<00:07, 27.8MB/s]\u001b[A\n",
"Downloading (…)l-00014-of-00033.bin: 54% 220M/405M [00:12<00:06, 27.8MB/s]\u001b[A\n",
"Downloading (…)l-00014-of-00033.bin: 57% 231M/405M [00:12<00:06, 27.8MB/s]\u001b[A\n",
"Downloading (…)l-00014-of-00033.bin: 60% 241M/405M [00:12<00:05, 27.9MB/s]\u001b[A\n",
"Downloading (…)l-00014-of-00033.bin: 62% 252M/405M [00:13<00:05, 27.9MB/s]\u001b[A\n",
"Downloading (…)l-00014-of-00033.bin: 65% 262M/405M [00:13<00:05, 27.9MB/s]\u001b[A\n",
"Downloading (…)l-00014-of-00033.bin: 67% 273M/405M [00:13<00:04, 27.9MB/s]\u001b[A\n",
"Downloading (…)l-00014-of-00033.bin: 70% 283M/405M [00:14<00:04, 27.9MB/s]\u001b[A\n",
"Downloading (…)l-00014-of-00033.bin: 73% 294M/405M [00:14<00:03, 27.9MB/s]\u001b[A\n",
"Downloading (…)l-00014-of-00033.bin: 75% 304M/405M [00:15<00:03, 27.9MB/s]\u001b[A\n",
"Downloading (…)l-00014-of-00033.bin: 78% 315M/405M [00:15<00:03, 27.9MB/s]\u001b[A\n",
"Downloading (…)l-00014-of-00033.bin: 80% 325M/405M [00:15<00:02, 27.8MB/s]\u001b[A\n",
"Downloading (…)l-00014-of-00033.bin: 83% 336M/405M [00:16<00:02, 27.9MB/s]\u001b[A\n",
"Downloading (…)l-00014-of-00033.bin: 85% 346M/405M [00:16<00:02, 27.9MB/s]\u001b[A\n",
"Downloading (…)l-00014-of-00033.bin: 88% 357M/405M [00:16<00:01, 27.9MB/s]\u001b[A\n",
"Downloading (…)l-00014-of-00033.bin: 91% 367M/405M [00:17<00:01, 27.9MB/s]\u001b[A\n",
"Downloading (…)l-00014-of-00033.bin: 93% 377M/405M [00:17<00:00, 27.9MB/s]\u001b[A\n",
"Downloading (…)l-00014-of-00033.bin: 96% 388M/405M [00:18<00:00, 27.9MB/s]\u001b[A\n",
"Downloading (…)l-00014-of-00033.bin: 98% 398M/405M [00:18<00:00, 27.9MB/s]\u001b[A\n",
"Downloading (…)l-00014-of-00033.bin: 100% 405M/405M [00:18<00:00, 21.7MB/s]\n",
"Downloading shards: 42% 14/33 [00:48<02:19, 7.34s/it]\n",
"Downloading (…)l-00015-of-00033.bin: 0% 0.00/405M [00:00<?, ?B/s]\u001b[A\n",
"Downloading (…)l-00015-of-00033.bin: 3% 10.5M/405M [00:02<01:20, 4.90MB/s]\u001b[A\n",
"Downloading (…)l-00015-of-00033.bin: 5% 21.0M/405M [00:03<00:54, 7.08MB/s]\u001b[A\n",
"Downloading (…)l-00015-of-00033.bin: 8% 31.5M/405M [00:03<00:40, 9.31MB/s]\u001b[A\n",
"Downloading (…)l-00015-of-00033.bin: 10% 41.9M/405M [00:04<00:30, 11.8MB/s]\u001b[A\n",
"Downloading (…)l-00015-of-00033.bin: 13% 52.4M/405M [00:04<00:24, 14.4MB/s]\u001b[A\n",
"Downloading (…)l-00015-of-00033.bin: 16% 62.9M/405M [00:05<00:19, 17.2MB/s]\u001b[A\n",
"Downloading (…)l-00015-of-00033.bin: 18% 73.4M/405M [00:05<00:16, 19.6MB/s]\u001b[A\n",
"Downloading (…)l-00015-of-00033.bin: 21% 83.9M/405M [00:05<00:14, 21.6MB/s]\u001b[A\n",
"Downloading (…)l-00015-of-00033.bin: 23% 94.4M/405M [00:06<00:13, 23.2MB/s]\u001b[A\n",
"Downloading (…)l-00015-of-00033.bin: 26% 105M/405M [00:06<00:12, 24.4MB/s] \u001b[A\n",
"Downloading (…)l-00015-of-00033.bin: 28% 115M/405M [00:07<00:11, 25.3MB/s]\u001b[A\n",
"Downloading (…)l-00015-of-00033.bin: 31% 126M/405M [00:07<00:10, 26.0MB/s]\u001b[A\n",
"Downloading (…)l-00015-of-00033.bin: 34% 136M/405M [00:07<00:10, 26.5MB/s]\u001b[A\n",
"Downloading (…)l-00015-of-00033.bin: 36% 147M/405M [00:08<00:09, 26.8MB/s]\u001b[A\n",
"Downloading (…)l-00015-of-00033.bin: 39% 157M/405M [00:08<00:09, 27.1MB/s]\u001b[A\n",
"Downloading (…)l-00015-of-00033.bin: 41% 168M/405M [00:09<00:08, 27.3MB/s]\u001b[A\n",
"Downloading (…)l-00015-of-00033.bin: 44% 178M/405M [00:09<00:08, 27.4MB/s]\u001b[A\n",
"Downloading (…)l-00015-of-00033.bin: 47% 189M/405M [00:09<00:07, 27.5MB/s]\u001b[A\n",
"Downloading (…)l-00015-of-00033.bin: 49% 199M/405M [00:10<00:07, 27.5MB/s]\u001b[A\n",
"Downloading (…)l-00015-of-00033.bin: 52% 210M/405M [00:10<00:07, 27.6MB/s]\u001b[A\n",
"Downloading (…)l-00015-of-00033.bin: 54% 220M/405M [00:10<00:06, 27.6MB/s]\u001b[A\n",
"Downloading (…)l-00015-of-00033.bin: 57% 231M/405M [00:11<00:06, 27.7MB/s]\u001b[A\n",
"Downloading (…)l-00015-of-00033.bin: 60% 241M/405M [00:11<00:05, 27.7MB/s]\u001b[A\n",
"Downloading (…)l-00015-of-00033.bin: 62% 252M/405M [00:12<00:05, 27.7MB/s]\u001b[A\n",
"Downloading (…)l-00015-of-00033.bin: 65% 262M/405M [00:12<00:05, 27.7MB/s]\u001b[A\n",
"Downloading (…)l-00015-of-00033.bin: 67% 273M/405M [00:12<00:04, 27.7MB/s]\u001b[A\n",
"Downloading (…)l-00015-of-00033.bin: 70% 283M/405M [00:13<00:04, 27.7MB/s]\u001b[A\n",
"Downloading (…)l-00015-of-00033.bin: 73% 294M/405M [00:13<00:04, 27.7MB/s]\u001b[A\n",
"Downloading (…)l-00015-of-00033.bin: 75% 304M/405M [00:13<00:03, 27.7MB/s]\u001b[A\n",
"Downloading (…)l-00015-of-00033.bin: 78% 315M/405M [00:14<00:03, 27.7MB/s]\u001b[A\n",
"Downloading (…)l-00015-of-00033.bin: 80% 325M/405M [00:14<00:02, 27.7MB/s]\u001b[A\n",
"Downloading (…)l-00015-of-00033.bin: 83% 336M/405M [00:15<00:02, 27.7MB/s]\u001b[A\n",
"Downloading (…)l-00015-of-00033.bin: 85% 346M/405M [00:15<00:02, 27.7MB/s]\u001b[A\n",
"Downloading (…)l-00015-of-00033.bin: 88% 357M/405M [00:15<00:01, 27.7MB/s]\u001b[A\n",
"Downloading (…)l-00015-of-00033.bin: 91% 367M/405M [00:16<00:01, 27.7MB/s]\u001b[A\n",
"Downloading (…)l-00015-of-00033.bin: 93% 377M/405M [00:16<00:00, 27.7MB/s]\u001b[A\n",
"Downloading (…)l-00015-of-00033.bin: 96% 388M/405M [00:16<00:00, 27.7MB/s]\u001b[A\n",
"Downloading (…)l-00015-of-00033.bin: 98% 398M/405M [00:17<00:00, 27.7MB/s]\u001b[A\n",
"Downloading (…)l-00015-of-00033.bin: 100% 405M/405M [00:17<00:00, 23.0MB/s]\n",
"Downloading shards: 45% 15/33 [01:06<03:10, 10.56s/it]\n",
"Downloading (…)l-00016-of-00033.bin: 0% 0.00/405M [00:00<?, ?B/s]\u001b[A\n",
"Downloading (…)l-00016-of-00033.bin: 3% 10.5M/405M [00:00<00:04, 91.8MB/s]\u001b[A\n",
"Downloading (…)l-00016-of-00033.bin: 8% 31.5M/405M [00:00<00:02, 144MB/s] \u001b[A\n",
"Downloading (…)l-00016-of-00033.bin: 13% 52.4M/405M [00:00<00:02, 171MB/s]\u001b[A\n",
"Downloading (…)l-00016-of-00033.bin: 18% 73.4M/405M [00:00<00:01, 185MB/s]\u001b[A\n",
"Downloading (…)l-00016-of-00033.bin: 23% 94.4M/405M [00:00<00:01, 189MB/s]\u001b[A\n",
"Downloading (…)l-00016-of-00033.bin: 28% 115M/405M [00:00<00:01, 191MB/s] \u001b[A\n",
"Downloading (…)l-00016-of-00033.bin: 36% 147M/405M [00:00<00:01, 202MB/s]\u001b[A\n",
"Downloading (…)l-00016-of-00033.bin: 41% 168M/405M [00:00<00:01, 204MB/s]\u001b[A\n",
"Downloading (…)l-00016-of-00033.bin: 47% 189M/405M [00:00<00:01, 205MB/s]\u001b[A\n",
"Downloading (…)l-00016-of-00033.bin: 52% 210M/405M [00:01<00:00, 206MB/s]\u001b[A\n",
"Downloading (…)l-00016-of-00033.bin: 57% 231M/405M [00:01<00:00, 204MB/s]\u001b[A\n",
"Downloading (…)l-00016-of-00033.bin: 62% 252M/405M [00:01<00:00, 199MB/s]\u001b[A\n",
"Downloading (…)l-00016-of-00033.bin: 67% 273M/405M [00:01<00:00, 201MB/s]\u001b[A\n",
"Downloading (…)l-00016-of-00033.bin: 73% 294M/405M [00:01<00:00, 203MB/s]\u001b[A\n",
"Downloading (…)l-00016-of-00033.bin: 78% 315M/405M [00:01<00:00, 205MB/s]\u001b[A\n",
"Downloading (…)l-00016-of-00033.bin: 83% 336M/405M [00:01<00:00, 206MB/s]\u001b[A\n",
"Downloading (…)l-00016-of-00033.bin: 88% 357M/405M [00:01<00:00, 207MB/s]\u001b[A\n",
"Downloading (…)l-00016-of-00033.bin: 93% 377M/405M [00:01<00:00, 207MB/s]\u001b[A\n",
"Downloading (…)l-00016-of-00033.bin: 100% 405M/405M [00:02<00:00, 196MB/s]\n",
"Downloading shards: 48% 16/33 [01:08<02:16, 8.06s/it]\n",
"Downloading (…)l-00017-of-00033.bin: 0% 0.00/405M [00:00<?, ?B/s]\u001b[A\n",
"Downloading (…)l-00017-of-00033.bin: 3% 10.5M/405M [00:00<00:04, 90.4MB/s]\u001b[A\n",
"Downloading (…)l-00017-of-00033.bin: 8% 31.5M/405M [00:00<00:02, 143MB/s] \u001b[A\n",
"Downloading (…)l-00017-of-00033.bin: 13% 52.4M/405M [00:00<00:02, 169MB/s]\u001b[A\n",
"Downloading (…)l-00017-of-00033.bin: 18% 73.4M/405M [00:00<00:01, 183MB/s]\u001b[A\n",
"Downloading (…)l-00017-of-00033.bin: 23% 94.4M/405M [00:00<00:01, 182MB/s]\u001b[A\n",
"Downloading (…)l-00017-of-00033.bin: 28% 115M/405M [00:00<00:01, 189MB/s] \u001b[A\n",
"Downloading (…)l-00017-of-00033.bin: 34% 136M/405M [00:00<00:01, 195MB/s]\u001b[A\n",
"Downloading (…)l-00017-of-00033.bin: 39% 157M/405M [00:00<00:01, 198MB/s]\u001b[A\n",
"Downloading (…)l-00017-of-00033.bin: 44% 178M/405M [00:00<00:01, 201MB/s]\u001b[A\n",
"Downloading (…)l-00017-of-00033.bin: 49% 199M/405M [00:01<00:01, 202MB/s]\u001b[A\n",
"Downloading (…)l-00017-of-00033.bin: 54% 220M/405M [00:01<00:00, 202MB/s]\u001b[A\n",
"Downloading (…)l-00017-of-00033.bin: 60% 241M/405M [00:01<00:00, 203MB/s]\u001b[A\n",
"Downloading (…)l-00017-of-00033.bin: 65% 262M/405M [00:01<00:00, 204MB/s]\u001b[A\n",
"Downloading (…)l-00017-of-00033.bin: 70% 283M/405M [00:01<00:00, 205MB/s]\u001b[A\n",
"Downloading (…)l-00017-of-00033.bin: 75% 304M/405M [00:01<00:00, 205MB/s]\u001b[A\n",
"Downloading (…)l-00017-of-00033.bin: 80% 325M/405M [00:01<00:00, 206MB/s]\u001b[A\n",
"Downloading (…)l-00017-of-00033.bin: 85% 346M/405M [00:01<00:00, 205MB/s]\u001b[A\n",
"Downloading (…)l-00017-of-00033.bin: 91% 367M/405M [00:01<00:00, 205MB/s]\u001b[A\n",
"Downloading (…)l-00017-of-00033.bin: 100% 405M/405M [00:02<00:00, 194MB/s]\n",
"Downloading shards: 52% 17/33 [01:10<01:40, 6.30s/it]\n",
"Downloading (…)l-00018-of-00033.bin: 0% 0.00/405M [00:00<?, ?B/s]\u001b[A\n",
"Downloading (…)l-00018-of-00033.bin: 3% 10.5M/405M [00:00<00:04, 89.0MB/s]\u001b[A\n",
"Downloading (…)l-00018-of-00033.bin: 8% 31.5M/405M [00:00<00:02, 144MB/s] \u001b[A\n",
"Downloading (…)l-00018-of-00033.bin: 13% 52.4M/405M [00:00<00:02, 170MB/s]\u001b[A\n",
"Downloading (…)l-00018-of-00033.bin: 18% 73.4M/405M [00:00<00:01, 183MB/s]\u001b[A\n",
"Downloading (…)l-00018-of-00033.bin: 23% 94.4M/405M [00:00<00:01, 190MB/s]\u001b[A\n",
"Downloading (…)l-00018-of-00033.bin: 28% 115M/405M [00:00<00:01, 194MB/s] \u001b[A\n",
"Downloading (…)l-00018-of-00033.bin: 34% 136M/405M [00:00<00:01, 197MB/s]\u001b[A\n",
"Downloading (…)l-00018-of-00033.bin: 39% 157M/405M [00:00<00:01, 199MB/s]\u001b[A\n",
"Downloading (…)l-00018-of-00033.bin: 44% 178M/405M [00:00<00:01, 200MB/s]\u001b[A\n",
"Downloading (…)l-00018-of-00033.bin: 49% 199M/405M [00:01<00:01, 201MB/s]\u001b[A\n",
"Downloading (…)l-00018-of-00033.bin: 54% 220M/405M [00:01<00:00, 202MB/s]\u001b[A\n",
"Downloading (…)l-00018-of-00033.bin: 60% 241M/405M [00:01<00:00, 199MB/s]\u001b[A\n",
"Downloading (…)l-00018-of-00033.bin: 65% 262M/405M [00:01<00:00, 198MB/s]\u001b[A\n",
"Downloading (…)l-00018-of-00033.bin: 70% 283M/405M [00:01<00:00, 199MB/s]\u001b[A\n",
"Downloading (…)l-00018-of-00033.bin: 75% 304M/405M [00:01<00:00, 200MB/s]\u001b[A\n",
"Downloading (…)l-00018-of-00033.bin: 80% 325M/405M [00:01<00:00, 194MB/s]\u001b[A\n",
"Downloading (…)l-00018-of-00033.bin: 85% 346M/405M [00:01<00:00, 197MB/s]\u001b[A\n",
"Downloading (…)l-00018-of-00033.bin: 91% 367M/405M [00:01<00:00, 199MB/s]\u001b[A\n",
"Downloading (…)l-00018-of-00033.bin: 100% 405M/405M [00:02<00:00, 192MB/s]\n",
"Downloading shards: 55% 18/33 [01:12<01:16, 5.09s/it]\n",
"Downloading (…)l-00019-of-00033.bin: 0% 0.00/405M [00:00<?, ?B/s]\u001b[A\n",
"Downloading (…)l-00019-of-00033.bin: 3% 10.5M/405M [00:00<00:04, 85.9MB/s]\u001b[A\n",
"Downloading (…)l-00019-of-00033.bin: 8% 31.5M/405M [00:00<00:02, 142MB/s] \u001b[A\n",
"Downloading (…)l-00019-of-00033.bin: 13% 52.4M/405M [00:00<00:02, 167MB/s]\u001b[A\n",
"Downloading (…)l-00019-of-00033.bin: 18% 73.4M/405M [00:00<00:01, 177MB/s]\u001b[A\n",
"Downloading (…)l-00019-of-00033.bin: 23% 94.4M/405M [00:00<00:01, 185MB/s]\u001b[A\n",
"Downloading (…)l-00019-of-00033.bin: 28% 115M/405M [00:00<00:01, 185MB/s] \u001b[A\n",
"Downloading (…)l-00019-of-00033.bin: 34% 136M/405M [00:00<00:01, 187MB/s]\u001b[A\n",
"Downloading (…)l-00019-of-00033.bin: 39% 157M/405M [00:00<00:01, 190MB/s]\u001b[A\n",
"Downloading (…)l-00019-of-00033.bin: 44% 178M/405M [00:00<00:01, 193MB/s]\u001b[A\n",
"Downloading (…)l-00019-of-00033.bin: 49% 199M/405M [00:01<00:01, 196MB/s]\u001b[A\n",
"Downloading (…)l-00019-of-00033.bin: 54% 220M/405M [00:01<00:00, 197MB/s]\u001b[A\n",
"Downloading (…)l-00019-of-00033.bin: 60% 241M/405M [00:01<00:00, 199MB/s]\u001b[A\n",
"Downloading (…)l-00019-of-00033.bin: 65% 262M/405M [00:01<00:00, 199MB/s]\u001b[A\n",
"Downloading (…)l-00019-of-00033.bin: 70% 283M/405M [00:01<00:00, 197MB/s]\u001b[A\n",
"Downloading (…)l-00019-of-00033.bin: 75% 304M/405M [00:01<00:00, 198MB/s]\u001b[A\n",
"Downloading (…)l-00019-of-00033.bin: 80% 325M/405M [00:01<00:00, 199MB/s]\u001b[A\n",
"Downloading (…)l-00019-of-00033.bin: 85% 346M/405M [00:01<00:00, 199MB/s]\u001b[A\n",
"Downloading (…)l-00019-of-00033.bin: 91% 367M/405M [00:01<00:00, 199MB/s]\u001b[A\n",
"Downloading (…)l-00019-of-00033.bin: 100% 405M/405M [00:02<00:00, 189MB/s]\n",
"Downloading shards: 58% 19/33 [01:15<00:59, 4.24s/it]\n",
"Downloading (…)l-00020-of-00033.bin: 0% 0.00/405M [00:00<?, ?B/s]\u001b[A\n",
"Downloading (…)l-00020-of-00033.bin: 3% 10.5M/405M [00:00<00:04, 85.8MB/s]\u001b[A\n",
"Downloading (…)l-00020-of-00033.bin: 8% 31.5M/405M [00:00<00:02, 144MB/s] \u001b[A\n",
"Downloading (…)l-00020-of-00033.bin: 13% 52.4M/405M [00:00<00:02, 169MB/s]\u001b[A\n",
"Downloading (…)l-00020-of-00033.bin: 18% 73.4M/405M [00:00<00:01, 181MB/s]\u001b[A\n",
"Downloading (…)l-00020-of-00033.bin: 23% 94.4M/405M [00:00<00:01, 189MB/s]\u001b[A\n",
"Downloading (…)l-00020-of-00033.bin: 28% 115M/405M [00:00<00:01, 191MB/s] \u001b[A\n",
"Downloading (…)l-00020-of-00033.bin: 34% 136M/405M [00:00<00:01, 192MB/s]\u001b[A\n",
"Downloading (…)l-00020-of-00033.bin: 39% 157M/405M [00:00<00:01, 185MB/s]\u001b[A\n",
"Downloading (…)l-00020-of-00033.bin: 44% 178M/405M [00:00<00:01, 190MB/s]\u001b[A\n",
"Downloading (…)l-00020-of-00033.bin: 49% 199M/405M [00:01<00:01, 193MB/s]\u001b[A\n",
"Downloading (…)l-00020-of-00033.bin: 54% 220M/405M [00:01<00:00, 196MB/s]\u001b[A\n",
"Downloading (…)l-00020-of-00033.bin: 60% 241M/405M [00:01<00:00, 198MB/s]\u001b[A\n",
"Downloading (…)l-00020-of-00033.bin: 65% 262M/405M [00:01<00:00, 198MB/s]\u001b[A\n",
"Downloading (…)l-00020-of-00033.bin: 70% 283M/405M [00:01<00:00, 199MB/s]\u001b[A\n",
"Downloading (…)l-00020-of-00033.bin: 75% 304M/405M [00:01<00:00, 200MB/s]\u001b[A\n",
"Downloading (…)l-00020-of-00033.bin: 80% 325M/405M [00:01<00:00, 201MB/s]\u001b[A\n",
"Downloading (…)l-00020-of-00033.bin: 88% 357M/405M [00:01<00:00, 205MB/s]\u001b[A\n",
"Downloading (…)l-00020-of-00033.bin: 93% 377M/405M [00:01<00:00, 206MB/s]\u001b[A\n",
"Downloading (…)l-00020-of-00033.bin: 100% 405M/405M [00:02<00:00, 192MB/s]\n",
"Downloading shards: 61% 20/33 [01:17<00:47, 3.64s/it]\n",
"Downloading (…)l-00021-of-00033.bin: 0% 0.00/405M [00:00<?, ?B/s]\u001b[A\n",
"Downloading (…)l-00021-of-00033.bin: 3% 10.5M/405M [00:00<00:04, 84.8MB/s]\u001b[A\n",
"Downloading (…)l-00021-of-00033.bin: 8% 31.5M/405M [00:00<00:02, 141MB/s] \u001b[A\n",
"Downloading (…)l-00021-of-00033.bin: 13% 52.4M/405M [00:00<00:02, 168MB/s]\u001b[A\n",
"Downloading (…)l-00021-of-00033.bin: 18% 73.4M/405M [00:00<00:01, 181MB/s]\u001b[A\n",
"Downloading (…)l-00021-of-00033.bin: 23% 94.4M/405M [00:00<00:01, 190MB/s]\u001b[A\n",
"Downloading (…)l-00021-of-00033.bin: 28% 115M/405M [00:00<00:01, 192MB/s] \u001b[A\n",
"Downloading (…)l-00021-of-00033.bin: 34% 136M/405M [00:00<00:01, 195MB/s]\u001b[A\n",
"Downloading (…)l-00021-of-00033.bin: 39% 157M/405M [00:00<00:01, 198MB/s]\u001b[A\n",
"Downloading (…)l-00021-of-00033.bin: 44% 178M/405M [00:00<00:01, 199MB/s]\u001b[A\n",
"Downloading (…)l-00021-of-00033.bin: 49% 199M/405M [00:01<00:01, 201MB/s]\u001b[A\n",
"Downloading (…)l-00021-of-00033.bin: 54% 220M/405M [00:01<00:00, 202MB/s]\u001b[A\n",
"Downloading (…)l-00021-of-00033.bin: 60% 241M/405M [00:01<00:00, 203MB/s]\u001b[A\n",
"Downloading (…)l-00021-of-00033.bin: 65% 262M/405M [00:01<00:00, 204MB/s]\u001b[A\n",
"Downloading (…)l-00021-of-00033.bin: 70% 283M/405M [00:01<00:00, 205MB/s]\u001b[A\n",
"Downloading (…)l-00021-of-00033.bin: 75% 304M/405M [00:01<00:00, 206MB/s]\u001b[A\n",
"Downloading (…)l-00021-of-00033.bin: 80% 325M/405M [00:01<00:00, 206MB/s]\u001b[A\n",
"Downloading (…)l-00021-of-00033.bin: 85% 346M/405M [00:01<00:00, 207MB/s]\u001b[A\n",
"Downloading (…)l-00021-of-00033.bin: 91% 367M/405M [00:01<00:00, 207MB/s]\u001b[A\n",
"Downloading (…)l-00021-of-00033.bin: 100% 405M/405M [00:02<00:00, 196MB/s]\n",
"Downloading shards: 64% 21/33 [01:19<00:38, 3.21s/it]\n",
"Downloading (…)l-00022-of-00033.bin: 0% 0.00/405M [00:00<?, ?B/s]\u001b[A\n",
"Downloading (…)l-00022-of-00033.bin: 3% 10.5M/405M [00:00<00:04, 89.8MB/s]\u001b[A\n",
"Downloading (…)l-00022-of-00033.bin: 8% 31.5M/405M [00:00<00:02, 147MB/s] \u001b[A\n",
"Downloading (…)l-00022-of-00033.bin: 13% 52.4M/405M [00:00<00:02, 169MB/s]\u001b[A\n",
"Downloading (…)l-00022-of-00033.bin: 18% 73.4M/405M [00:00<00:01, 179MB/s]\u001b[A\n",
"Downloading (…)l-00022-of-00033.bin: 23% 94.4M/405M [00:00<00:01, 189MB/s]\u001b[A\n",
"Downloading (…)l-00022-of-00033.bin: 28% 115M/405M [00:00<00:01, 194MB/s] \u001b[A\n",
"Downloading (…)l-00022-of-00033.bin: 34% 136M/405M [00:00<00:01, 196MB/s]\u001b[A\n",
"Downloading (…)l-00022-of-00033.bin: 39% 157M/405M [00:00<00:01, 193MB/s]\u001b[A\n",
"Downloading (…)l-00022-of-00033.bin: 44% 178M/405M [00:00<00:01, 197MB/s]\u001b[A\n",
"Downloading (…)l-00022-of-00033.bin: 49% 199M/405M [00:01<00:01, 199MB/s]\u001b[A\n",
"Downloading (…)l-00022-of-00033.bin: 54% 220M/405M [00:01<00:00, 200MB/s]\u001b[A\n",
"Downloading (…)l-00022-of-00033.bin: 60% 241M/405M [00:01<00:00, 200MB/s]\u001b[A\n",
"Downloading (…)l-00022-of-00033.bin: 65% 262M/405M [00:01<00:00, 202MB/s]\u001b[A\n",
"Downloading (…)l-00022-of-00033.bin: 70% 283M/405M [00:01<00:00, 203MB/s]\u001b[A\n",
"Downloading (…)l-00022-of-00033.bin: 75% 304M/405M [00:01<00:00, 203MB/s]\u001b[A\n",
"Downloading (…)l-00022-of-00033.bin: 80% 325M/405M [00:01<00:00, 202MB/s]\u001b[A\n",
"Downloading (…)l-00022-of-00033.bin: 85% 346M/405M [00:01<00:00, 199MB/s]\u001b[A\n",
"Downloading (…)l-00022-of-00033.bin: 91% 367M/405M [00:01<00:00, 200MB/s]\u001b[A\n",
"Downloading (…)l-00022-of-00033.bin: 100% 405M/405M [00:02<00:00, 193MB/s]\n",
"Downloading shards: 67% 22/33 [01:21<00:32, 2.92s/it]\n",
"Downloading (…)l-00023-of-00033.bin: 0% 0.00/405M [00:00<?, ?B/s]\u001b[A\n",
"Downloading (…)l-00023-of-00033.bin: 3% 10.5M/405M [00:00<00:04, 92.9MB/s]\u001b[A\n",
"Downloading (…)l-00023-of-00033.bin: 8% 31.5M/405M [00:00<00:02, 153MB/s] \u001b[A\n",
"Downloading (…)l-00023-of-00033.bin: 13% 52.4M/405M [00:00<00:01, 176MB/s]\u001b[A\n",
"Downloading (…)l-00023-of-00033.bin: 18% 73.4M/405M [00:00<00:01, 188MB/s]\u001b[A\n",
"Downloading (…)l-00023-of-00033.bin: 23% 94.4M/405M [00:00<00:01, 195MB/s]\u001b[A\n",
"Downloading (…)l-00023-of-00033.bin: 28% 115M/405M [00:00<00:01, 199MB/s] \u001b[A\n",
"Downloading (…)l-00023-of-00033.bin: 34% 136M/405M [00:00<00:01, 202MB/s]\u001b[A\n",
"Downloading (…)l-00023-of-00033.bin: 39% 157M/405M [00:00<00:01, 204MB/s]\u001b[A\n",
"Downloading (…)l-00023-of-00033.bin: 44% 178M/405M [00:00<00:01, 204MB/s]\u001b[A\n",
"Downloading (…)l-00023-of-00033.bin: 49% 199M/405M [00:01<00:01, 201MB/s]\u001b[A\n",
"Downloading (…)l-00023-of-00033.bin: 54% 220M/405M [00:01<00:00, 199MB/s]\u001b[A\n",
"Downloading (…)l-00023-of-00033.bin: 60% 241M/405M [00:01<00:00, 202MB/s]\u001b[A\n",
"Downloading (…)l-00023-of-00033.bin: 65% 262M/405M [00:01<00:00, 203MB/s]\u001b[A\n",
"Downloading (…)l-00023-of-00033.bin: 70% 283M/405M [00:01<00:00, 204MB/s]\u001b[A\n",
"Downloading (…)l-00023-of-00033.bin: 75% 304M/405M [00:01<00:00, 205MB/s]\u001b[A\n",
"Downloading (…)l-00023-of-00033.bin: 80% 325M/405M [00:01<00:00, 205MB/s]\u001b[A\n",
"Downloading (…)l-00023-of-00033.bin: 85% 346M/405M [00:01<00:00, 206MB/s]\u001b[A\n",
"Downloading (…)l-00023-of-00033.bin: 91% 367M/405M [00:01<00:00, 204MB/s]\u001b[A\n",
"Downloading (…)l-00023-of-00033.bin: 100% 405M/405M [00:02<00:00, 197MB/s]\n",
"Downloading shards: 70% 23/33 [01:23<00:27, 2.70s/it]\n",
"Downloading (…)l-00024-of-00033.bin: 0% 0.00/405M [00:00<?, ?B/s]\u001b[A\n",
"Downloading (…)l-00024-of-00033.bin: 3% 10.5M/405M [00:00<00:04, 93.8MB/s]\u001b[A\n",
"Downloading (…)l-00024-of-00033.bin: 8% 31.5M/405M [00:00<00:02, 152MB/s] \u001b[A\n",
"Downloading (…)l-00024-of-00033.bin: 13% 52.4M/405M [00:00<00:01, 177MB/s]\u001b[A\n",
"Downloading (…)l-00024-of-00033.bin: 21% 83.9M/405M [00:00<00:01, 193MB/s]\u001b[A\n",
"Downloading (…)l-00024-of-00033.bin: 28% 115M/405M [00:00<00:01, 200MB/s] \u001b[A\n",
"Downloading (…)l-00024-of-00033.bin: 34% 136M/405M [00:00<00:01, 203MB/s]\u001b[A\n",
"Downloading (…)l-00024-of-00033.bin: 41% 168M/405M [00:00<00:01, 206MB/s]\u001b[A\n",
"Downloading (…)l-00024-of-00033.bin: 49% 199M/405M [00:01<00:00, 207MB/s]\u001b[A\n",
"Downloading (…)l-00024-of-00033.bin: 57% 231M/405M [00:01<00:00, 207MB/s]\u001b[A\n",
"Downloading (…)l-00024-of-00033.bin: 62% 252M/405M [00:01<00:00, 205MB/s]\u001b[A\n",
"Downloading (…)l-00024-of-00033.bin: 67% 273M/405M [00:01<00:00, 203MB/s]\u001b[A\n",
"Downloading (…)l-00024-of-00033.bin: 73% 294M/405M [00:01<00:00, 204MB/s]\u001b[A\n",
"Downloading (…)l-00024-of-00033.bin: 80% 325M/405M [00:01<00:00, 205MB/s]\u001b[A\n",
"Downloading (…)l-00024-of-00033.bin: 85% 346M/405M [00:01<00:00, 204MB/s]\u001b[A\n",
"Downloading (…)l-00024-of-00033.bin: 93% 377M/405M [00:01<00:00, 207MB/s]\u001b[A\n",
"Downloading (…)l-00024-of-00033.bin: 100% 405M/405M [00:02<00:00, 199MB/s]\n",
"Downloading shards: 73% 24/33 [01:26<00:22, 2.54s/it]\n",
"Downloading (…)l-00025-of-00033.bin: 0% 0.00/405M [00:00<?, ?B/s]\u001b[A\n",
"Downloading (…)l-00025-of-00033.bin: 3% 10.5M/405M [00:00<00:04, 92.7MB/s]\u001b[A\n",
"Downloading (…)l-00025-of-00033.bin: 8% 31.5M/405M [00:00<00:02, 152MB/s] \u001b[A\n",
"Downloading (…)l-00025-of-00033.bin: 13% 52.4M/405M [00:00<00:02, 175MB/s]\u001b[A\n",
"Downloading (…)l-00025-of-00033.bin: 18% 73.4M/405M [00:00<00:01, 188MB/s]\u001b[A\n",
"Downloading (…)l-00025-of-00033.bin: 23% 94.4M/405M [00:00<00:01, 193MB/s]\u001b[A\n",
"Downloading (…)l-00025-of-00033.bin: 28% 115M/405M [00:00<00:01, 195MB/s] \u001b[A\n",
"Downloading (…)l-00025-of-00033.bin: 34% 136M/405M [00:00<00:01, 197MB/s]\u001b[A\n",
"Downloading (…)l-00025-of-00033.bin: 39% 157M/405M [00:00<00:01, 200MB/s]\u001b[A\n",
"Downloading (…)l-00025-of-00033.bin: 44% 178M/405M [00:00<00:01, 202MB/s]\u001b[A\n",
"Downloading (…)l-00025-of-00033.bin: 49% 199M/405M [00:01<00:01, 205MB/s]\u001b[A\n",
"Downloading (…)l-00025-of-00033.bin: 54% 220M/405M [00:01<00:00, 206MB/s]\u001b[A\n",
"Downloading (…)l-00025-of-00033.bin: 60% 241M/405M [00:01<00:00, 206MB/s]\u001b[A\n",
"Downloading (…)l-00025-of-00033.bin: 65% 262M/405M [00:01<00:00, 207MB/s]\u001b[A\n",
"Downloading (…)l-00025-of-00033.bin: 70% 283M/405M [00:01<00:00, 207MB/s]\u001b[A\n",
"Downloading (…)l-00025-of-00033.bin: 75% 304M/405M [00:01<00:00, 207MB/s]\u001b[A\n",
"Downloading (…)l-00025-of-00033.bin: 80% 325M/405M [00:01<00:00, 207MB/s]\u001b[A\n",
"Downloading (…)l-00025-of-00033.bin: 85% 346M/405M [00:01<00:00, 207MB/s]\u001b[A\n",
"Downloading (…)l-00025-of-00033.bin: 91% 367M/405M [00:01<00:00, 208MB/s]\u001b[A\n",
"Downloading (…)l-00025-of-00033.bin: 100% 405M/405M [00:02<00:00, 198MB/s]\n",
"Downloading shards: 76% 25/33 [01:28<00:19, 2.43s/it]\n",
"Downloading (…)l-00026-of-00033.bin: 0% 0.00/405M [00:00<?, ?B/s]\u001b[A\n",
"Downloading (…)l-00026-of-00033.bin: 3% 10.5M/405M [00:00<00:04, 88.3MB/s]\u001b[A\n",
"Downloading (…)l-00026-of-00033.bin: 8% 31.5M/405M [00:00<00:02, 148MB/s] \u001b[A\n",
"Downloading (…)l-00026-of-00033.bin: 13% 52.4M/405M [00:00<00:02, 174MB/s]\u001b[A\n",
"Downloading (…)l-00026-of-00033.bin: 18% 73.4M/405M [00:00<00:01, 187MB/s]\u001b[A\n",
"Downloading (…)l-00026-of-00033.bin: 23% 94.4M/405M [00:00<00:01, 194MB/s]\u001b[A\n",
"Downloading (…)l-00026-of-00033.bin: 28% 115M/405M [00:00<00:01, 199MB/s] \u001b[A\n",
"Downloading (…)l-00026-of-00033.bin: 34% 136M/405M [00:00<00:01, 202MB/s]\u001b[A\n",
"Downloading (…)l-00026-of-00033.bin: 39% 157M/405M [00:00<00:01, 204MB/s]\u001b[A\n",
"Downloading (…)l-00026-of-00033.bin: 44% 178M/405M [00:00<00:01, 205MB/s]\u001b[A\n",
"Downloading (…)l-00026-of-00033.bin: 49% 199M/405M [00:01<00:00, 206MB/s]\u001b[A\n",
"Downloading (…)l-00026-of-00033.bin: 54% 220M/405M [00:01<00:00, 195MB/s]\u001b[A\n",
"Downloading (…)l-00026-of-00033.bin: 60% 241M/405M [00:01<00:00, 199MB/s]\u001b[A\n",
"Downloading (…)l-00026-of-00033.bin: 65% 262M/405M [00:01<00:00, 201MB/s]\u001b[A\n",
"Downloading (…)l-00026-of-00033.bin: 70% 283M/405M [00:01<00:00, 203MB/s]\u001b[A\n",
"Downloading (…)l-00026-of-00033.bin: 78% 315M/405M [00:01<00:00, 206MB/s]\u001b[A\n",
"Downloading (…)l-00026-of-00033.bin: 83% 336M/405M [00:01<00:00, 207MB/s]\u001b[A\n",
"Downloading (…)l-00026-of-00033.bin: 88% 357M/405M [00:01<00:00, 206MB/s]\u001b[A\n",
"Downloading (…)l-00026-of-00033.bin: 93% 377M/405M [00:01<00:00, 204MB/s]\u001b[A\n",
"Downloading (…)l-00026-of-00033.bin: 100% 405M/405M [00:02<00:00, 196MB/s]\n",
"Downloading shards: 79% 26/33 [01:30<00:16, 2.37s/it]\n",
"Downloading (…)l-00027-of-00033.bin: 0% 0.00/405M [00:00<?, ?B/s]\u001b[A\n",
"Downloading (…)l-00027-of-00033.bin: 3% 10.5M/405M [00:00<00:04, 92.8MB/s]\u001b[A\n",
"Downloading (…)l-00027-of-00033.bin: 8% 31.5M/405M [00:00<00:02, 153MB/s] \u001b[A\n",
"Downloading (…)l-00027-of-00033.bin: 13% 52.4M/405M [00:00<00:01, 177MB/s]\u001b[A\n",
"Downloading (…)l-00027-of-00033.bin: 18% 73.4M/405M [00:00<00:01, 188MB/s]\u001b[A\n",
"Downloading (…)l-00027-of-00033.bin: 23% 94.4M/405M [00:00<00:01, 195MB/s]\u001b[A\n",
"Downloading (…)l-00027-of-00033.bin: 31% 126M/405M [00:00<00:01, 203MB/s] \u001b[A\n",
"Downloading (…)l-00027-of-00033.bin: 36% 147M/405M [00:00<00:01, 204MB/s]\u001b[A\n",
"Downloading (…)l-00027-of-00033.bin: 41% 168M/405M [00:00<00:01, 205MB/s]\u001b[A\n",
"Downloading (…)l-00027-of-00033.bin: 47% 189M/405M [00:00<00:01, 205MB/s]\u001b[A\n",
"Downloading (…)l-00027-of-00033.bin: 52% 210M/405M [00:01<00:00, 206MB/s]\u001b[A\n",
"Downloading (…)l-00027-of-00033.bin: 57% 231M/405M [00:01<00:00, 205MB/s]\u001b[A\n",
"Downloading (…)l-00027-of-00033.bin: 62% 252M/405M [00:01<00:00, 203MB/s]\u001b[A\n",
"Downloading (…)l-00027-of-00033.bin: 67% 273M/405M [00:01<00:00, 199MB/s]\u001b[A\n",
"Downloading (…)l-00027-of-00033.bin: 73% 294M/405M [00:01<00:00, 202MB/s]\u001b[A\n",
"Downloading (…)l-00027-of-00033.bin: 78% 315M/405M [00:01<00:00, 204MB/s]\u001b[A\n",
"Downloading (…)l-00027-of-00033.bin: 83% 336M/405M [00:01<00:00, 205MB/s]\u001b[A\n",
"Downloading (…)l-00027-of-00033.bin: 88% 357M/405M [00:01<00:00, 206MB/s]\u001b[A\n",
"Downloading (…)l-00027-of-00033.bin: 93% 377M/405M [00:01<00:00, 207MB/s]\u001b[A\n",
"Downloading (…)l-00027-of-00033.bin: 100% 405M/405M [00:02<00:00, 198MB/s]\n",
"Downloading shards: 82% 27/33 [01:32<00:13, 2.31s/it]\n",
"Downloading (…)l-00028-of-00033.bin: 0% 0.00/405M [00:00<?, ?B/s]\u001b[A\n",
"Downloading (…)l-00028-of-00033.bin: 3% 10.5M/405M [00:00<00:04, 92.9MB/s]\u001b[A\n",
"Downloading (…)l-00028-of-00033.bin: 8% 31.5M/405M [00:00<00:02, 154MB/s] \u001b[A\n",
"Downloading (…)l-00028-of-00033.bin: 13% 52.4M/405M [00:00<00:01, 176MB/s]\u001b[A\n",
"Downloading (…)l-00028-of-00033.bin: 18% 73.4M/405M [00:00<00:01, 188MB/s]\u001b[A\n",
"Downloading (…)l-00028-of-00033.bin: 23% 94.4M/405M [00:00<00:01, 194MB/s]\u001b[A\n",
"Downloading (…)l-00028-of-00033.bin: 28% 115M/405M [00:00<00:01, 199MB/s] \u001b[A\n",
"Downloading (…)l-00028-of-00033.bin: 34% 136M/405M [00:00<00:01, 201MB/s]\u001b[A\n",
"Downloading (…)l-00028-of-00033.bin: 39% 157M/405M [00:00<00:01, 199MB/s]\u001b[A\n",
"Downloading (…)l-00028-of-00033.bin: 44% 178M/405M [00:00<00:01, 199MB/s]\u001b[A\n",
"Downloading (…)l-00028-of-00033.bin: 49% 199M/405M [00:01<00:01, 200MB/s]\u001b[A\n",
"Downloading (…)l-00028-of-00033.bin: 54% 220M/405M [00:01<00:00, 201MB/s]\u001b[A\n",
"Downloading (…)l-00028-of-00033.bin: 60% 241M/405M [00:01<00:00, 198MB/s]\u001b[A\n",
"Downloading (…)l-00028-of-00033.bin: 65% 262M/405M [00:01<00:00, 190MB/s]\u001b[A\n",
"Downloading (…)l-00028-of-00033.bin: 70% 283M/405M [00:01<00:00, 193MB/s]\u001b[A\n",
"Downloading (…)l-00028-of-00033.bin: 75% 304M/405M [00:01<00:00, 195MB/s]\u001b[A\n",
"Downloading (…)l-00028-of-00033.bin: 80% 325M/405M [00:01<00:00, 197MB/s]\u001b[A\n",
"Downloading (…)l-00028-of-00033.bin: 85% 346M/405M [00:01<00:00, 198MB/s]\u001b[A\n",
"Downloading (…)l-00028-of-00033.bin: 91% 367M/405M [00:01<00:00, 199MB/s]\u001b[A\n",
"Downloading (…)l-00028-of-00033.bin: 100% 405M/405M [00:02<00:00, 193MB/s]\n",
"Downloading shards: 85% 28/33 [01:34<00:11, 2.29s/it]\n",
"Downloading (…)l-00029-of-00033.bin: 0% 0.00/405M [00:00<?, ?B/s]\u001b[A\n",
"Downloading (…)l-00029-of-00033.bin: 3% 10.5M/405M [00:00<00:04, 91.7MB/s]\u001b[A\n",
"Downloading (…)l-00029-of-00033.bin: 8% 31.5M/405M [00:00<00:02, 149MB/s] \u001b[A\n",
"Downloading (…)l-00029-of-00033.bin: 13% 52.4M/405M [00:00<00:02, 173MB/s]\u001b[A\n",
"Downloading (…)l-00029-of-00033.bin: 18% 73.4M/405M [00:00<00:01, 175MB/s]\u001b[A\n",
"Downloading (…)l-00029-of-00033.bin: 23% 94.4M/405M [00:00<00:01, 185MB/s]\u001b[A\n",
"Downloading (…)l-00029-of-00033.bin: 28% 115M/405M [00:00<00:01, 191MB/s] \u001b[A\n",
"Downloading (…)l-00029-of-00033.bin: 34% 136M/405M [00:00<00:01, 194MB/s]\u001b[A\n",
"Downloading (…)l-00029-of-00033.bin: 39% 157M/405M [00:00<00:01, 194MB/s]\u001b[A\n",
"Downloading (…)l-00029-of-00033.bin: 44% 178M/405M [00:00<00:01, 193MB/s]\u001b[A\n",
"Downloading (…)l-00029-of-00033.bin: 49% 199M/405M [00:01<00:01, 196MB/s]\u001b[A\n",
"Downloading (…)l-00029-of-00033.bin: 54% 220M/405M [00:01<00:00, 198MB/s]\u001b[A\n",
"Downloading (…)l-00029-of-00033.bin: 60% 241M/405M [00:01<00:00, 200MB/s]\u001b[A\n",
"Downloading (…)l-00029-of-00033.bin: 65% 262M/405M [00:01<00:00, 200MB/s]\u001b[A\n",
"Downloading (…)l-00029-of-00033.bin: 70% 283M/405M [00:01<00:00, 201MB/s]\u001b[A\n",
"Downloading (…)l-00029-of-00033.bin: 75% 304M/405M [00:01<00:00, 202MB/s]\u001b[A\n",
"Downloading (…)l-00029-of-00033.bin: 80% 325M/405M [00:01<00:00, 201MB/s]\u001b[A\n",
"Downloading (…)l-00029-of-00033.bin: 85% 346M/405M [00:01<00:00, 202MB/s]\u001b[A\n",
"Downloading (…)l-00029-of-00033.bin: 91% 367M/405M [00:01<00:00, 202MB/s]\u001b[A\n",
"Downloading (…)l-00029-of-00033.bin: 100% 405M/405M [00:02<00:00, 192MB/s]\n",
"Downloading shards: 88% 29/33 [01:37<00:09, 2.28s/it]\n",
"Downloading (…)l-00030-of-00033.bin: 0% 0.00/405M [00:00<?, ?B/s]\u001b[A\n",
"Downloading (…)l-00030-of-00033.bin: 3% 10.5M/405M [00:00<00:04, 89.7MB/s]\u001b[A\n",
"Downloading (…)l-00030-of-00033.bin: 8% 31.5M/405M [00:00<00:02, 149MB/s] \u001b[A\n",
"Downloading (…)l-00030-of-00033.bin: 13% 52.4M/405M [00:00<00:02, 173MB/s]\u001b[A\n",
"Downloading (…)l-00030-of-00033.bin: 18% 73.4M/405M [00:00<00:01, 186MB/s]\u001b[A\n",
"Downloading (…)l-00030-of-00033.bin: 23% 94.4M/405M [00:00<00:01, 193MB/s]\u001b[A\n",
"Downloading (…)l-00030-of-00033.bin: 28% 115M/405M [00:00<00:01, 197MB/s] \u001b[A\n",
"Downloading (…)l-00030-of-00033.bin: 34% 136M/405M [00:00<00:01, 201MB/s]\u001b[A\n",
"Downloading (…)l-00030-of-00033.bin: 39% 157M/405M [00:00<00:01, 203MB/s]\u001b[A\n",
"Downloading (…)l-00030-of-00033.bin: 44% 178M/405M [00:00<00:01, 203MB/s]\u001b[A\n",
"Downloading (…)l-00030-of-00033.bin: 49% 199M/405M [00:01<00:01, 205MB/s]\u001b[A\n",
"Downloading (…)l-00030-of-00033.bin: 54% 220M/405M [00:01<00:00, 205MB/s]\u001b[A\n",
"Downloading (…)l-00030-of-00033.bin: 60% 241M/405M [00:01<00:00, 202MB/s]\u001b[A\n",
"Downloading (…)l-00030-of-00033.bin: 65% 262M/405M [00:01<00:00, 187MB/s]\u001b[A\n",
"Downloading (…)l-00030-of-00033.bin: 70% 283M/405M [00:01<00:00, 190MB/s]\u001b[A\n",
"Downloading (…)l-00030-of-00033.bin: 75% 304M/405M [00:01<00:00, 193MB/s]\u001b[A\n",
"Downloading (…)l-00030-of-00033.bin: 80% 325M/405M [00:01<00:00, 196MB/s]\u001b[A\n",
"Downloading (…)l-00030-of-00033.bin: 85% 346M/405M [00:01<00:00, 197MB/s]\u001b[A\n",
"Downloading (…)l-00030-of-00033.bin: 91% 367M/405M [00:01<00:00, 200MB/s]\u001b[A\n",
"Downloading (…)l-00030-of-00033.bin: 100% 405M/405M [00:02<00:00, 192MB/s]\n",
"Downloading shards: 91% 30/33 [01:39<00:06, 2.27s/it]\n",
"Downloading (…)l-00031-of-00033.bin: 0% 0.00/405M [00:00<?, ?B/s]\u001b[A\n",
"Downloading (…)l-00031-of-00033.bin: 3% 10.5M/405M [00:00<00:05, 70.4MB/s]\u001b[A\n",
"Downloading (…)l-00031-of-00033.bin: 5% 21.0M/405M [00:00<00:04, 82.7MB/s]\u001b[A\n",
"Downloading (…)l-00031-of-00033.bin: 8% 31.5M/405M [00:00<00:04, 84.8MB/s]\u001b[A\n",
"Downloading (…)l-00031-of-00033.bin: 10% 41.9M/405M [00:00<00:04, 87.9MB/s]\u001b[A\n",
"Downloading (…)l-00031-of-00033.bin: 13% 52.4M/405M [00:00<00:03, 89.8MB/s]\u001b[A\n",
"Downloading (…)l-00031-of-00033.bin: 16% 62.9M/405M [00:00<00:03, 90.0MB/s]\u001b[A\n",
"Downloading (…)l-00031-of-00033.bin: 18% 73.4M/405M [00:00<00:03, 86.3MB/s]\u001b[A\n",
"Downloading (…)l-00031-of-00033.bin: 21% 83.9M/405M [00:00<00:03, 87.6MB/s]\u001b[A\n",
"Downloading (…)l-00031-of-00033.bin: 23% 94.4M/405M [00:01<00:03, 78.5MB/s]\u001b[A\n",
"Downloading (…)l-00031-of-00033.bin: 26% 105M/405M [00:01<00:03, 80.1MB/s] \u001b[A\n",
"Downloading (…)l-00031-of-00033.bin: 28% 115M/405M [00:01<00:03, 84.6MB/s]\u001b[A\n",
"Downloading (…)l-00031-of-00033.bin: 31% 126M/405M [00:01<00:03, 82.3MB/s]\u001b[A\n",
"Downloading (…)l-00031-of-00033.bin: 34% 136M/405M [00:01<00:03, 85.8MB/s]\u001b[A\n",
"Downloading (…)l-00031-of-00033.bin: 36% 147M/405M [00:01<00:02, 88.7MB/s]\u001b[A\n",
"Downloading (…)l-00031-of-00033.bin: 39% 157M/405M [00:01<00:02, 87.0MB/s]\u001b[A\n",
"Downloading (…)l-00031-of-00033.bin: 41% 168M/405M [00:01<00:02, 87.9MB/s]\u001b[A\n",
"Downloading (…)l-00031-of-00033.bin: 44% 178M/405M [00:02<00:02, 90.2MB/s]\u001b[A\n",
"Downloading (…)l-00031-of-00033.bin: 47% 189M/405M [00:02<00:02, 90.6MB/s]\u001b[A\n",
"Downloading (…)l-00031-of-00033.bin: 49% 199M/405M [00:02<00:02, 89.6MB/s]\u001b[A\n",
"Downloading (…)l-00031-of-00033.bin: 52% 210M/405M [00:02<00:02, 92.6MB/s]\u001b[A\n",
"Downloading (…)l-00031-of-00033.bin: 54% 220M/405M [00:02<00:02, 88.2MB/s]\u001b[A\n",
"Downloading (…)l-00031-of-00033.bin: 57% 231M/405M [00:02<00:01, 90.8MB/s]\u001b[A\n",
"Downloading (…)l-00031-of-00033.bin: 60% 241M/405M [00:02<00:01, 91.7MB/s]\u001b[A\n",
"Downloading (…)l-00031-of-00033.bin: 62% 252M/405M [00:02<00:01, 91.5MB/s]\u001b[A\n",
"Downloading (…)l-00031-of-00033.bin: 65% 262M/405M [00:02<00:01, 91.7MB/s]\u001b[A\n",
"Downloading (…)l-00031-of-00033.bin: 67% 273M/405M [00:03<00:01, 91.4MB/s]\u001b[A\n",
"Downloading (…)l-00031-of-00033.bin: 70% 283M/405M [00:03<00:01, 93.7MB/s]\u001b[A\n",
"Downloading (…)l-00031-of-00033.bin: 73% 294M/405M [00:03<00:01, 93.9MB/s]\u001b[A\n",
"Downloading (…)l-00031-of-00033.bin: 75% 304M/405M [00:03<00:01, 94.9MB/s]\u001b[A\n",
"Downloading (…)l-00031-of-00033.bin: 78% 315M/405M [00:03<00:00, 92.4MB/s]\u001b[A\n",
"Downloading (…)l-00031-of-00033.bin: 80% 325M/405M [00:03<00:00, 91.3MB/s]\u001b[A\n",
"Downloading (…)l-00031-of-00033.bin: 83% 336M/405M [00:03<00:00, 91.2MB/s]\u001b[A\n",
"Downloading (…)l-00031-of-00033.bin: 85% 346M/405M [00:03<00:00, 89.0MB/s]\u001b[A\n",
"Downloading (…)l-00031-of-00033.bin: 88% 357M/405M [00:04<00:00, 91.1MB/s]\u001b[A\n",
"Downloading (…)l-00031-of-00033.bin: 91% 367M/405M [00:04<00:00, 92.1MB/s]\u001b[A\n",
"Downloading (…)l-00031-of-00033.bin: 93% 377M/405M [00:04<00:00, 93.2MB/s]\u001b[A\n",
"Downloading (…)l-00031-of-00033.bin: 96% 388M/405M [00:04<00:00, 93.6MB/s]\u001b[A\n",
"Downloading (…)l-00031-of-00033.bin: 100% 405M/405M [00:04<00:00, 89.2MB/s]\n",
"Downloading shards: 94% 31/33 [01:44<00:06, 3.01s/it]\n",
"Downloading (…)l-00032-of-00033.bin: 0% 0.00/405M [00:00<?, ?B/s]\u001b[A\n",
"Downloading (…)l-00032-of-00033.bin: 3% 10.5M/405M [00:00<00:05, 72.1MB/s]\u001b[A\n",
"Downloading (…)l-00032-of-00033.bin: 5% 21.0M/405M [00:00<00:04, 84.6MB/s]\u001b[A\n",
"Downloading (…)l-00032-of-00033.bin: 8% 31.5M/405M [00:00<00:04, 90.3MB/s]\u001b[A\n",
"Downloading (…)l-00032-of-00033.bin: 10% 41.9M/405M [00:00<00:03, 92.3MB/s]\u001b[A\n",
"Downloading (…)l-00032-of-00033.bin: 13% 52.4M/405M [00:00<00:03, 92.0MB/s]\u001b[A\n",
"Downloading (…)l-00032-of-00033.bin: 16% 62.9M/405M [00:00<00:03, 93.0MB/s]\u001b[A\n",
"Downloading (…)l-00032-of-00033.bin: 18% 73.4M/405M [00:00<00:03, 93.6MB/s]\u001b[A\n",
"Downloading (…)l-00032-of-00033.bin: 21% 83.9M/405M [00:00<00:03, 94.5MB/s]\u001b[A\n",
"Downloading (…)l-00032-of-00033.bin: 23% 94.4M/405M [00:01<00:03, 94.9MB/s]\u001b[A\n",
"Downloading (…)l-00032-of-00033.bin: 26% 105M/405M [00:01<00:03, 96.0MB/s] \u001b[A\n",
"Downloading (…)l-00032-of-00033.bin: 28% 115M/405M [00:01<00:03, 96.2MB/s]\u001b[A\n",
"Downloading (…)l-00032-of-00033.bin: 31% 126M/405M [00:01<00:02, 94.7MB/s]\u001b[A\n",
"Downloading (…)l-00032-of-00033.bin: 34% 136M/405M [00:01<00:03, 88.4MB/s]\u001b[A\n",
"Downloading (…)l-00032-of-00033.bin: 36% 147M/405M [00:01<00:02, 88.4MB/s]\u001b[A\n",
"Downloading (…)l-00032-of-00033.bin: 39% 157M/405M [00:01<00:02, 90.1MB/s]\u001b[A\n",
"Downloading (…)l-00032-of-00033.bin: 41% 168M/405M [00:01<00:02, 91.8MB/s]\u001b[A\n",
"Downloading (…)l-00032-of-00033.bin: 44% 178M/405M [00:01<00:02, 92.5MB/s]\u001b[A\n",
"Downloading (…)l-00032-of-00033.bin: 47% 189M/405M [00:02<00:02, 91.0MB/s]\u001b[A\n",
"Downloading (…)l-00032-of-00033.bin: 49% 199M/405M [00:02<00:02, 91.9MB/s]\u001b[A\n",
"Downloading (…)l-00032-of-00033.bin: 52% 210M/405M [00:02<00:02, 92.8MB/s]\u001b[A\n",
"Downloading (…)l-00032-of-00033.bin: 54% 220M/405M [00:02<00:02, 89.9MB/s]\u001b[A\n",
"Downloading (…)l-00032-of-00033.bin: 57% 231M/405M [00:02<00:01, 90.4MB/s]\u001b[A\n",
"Downloading (…)l-00032-of-00033.bin: 60% 241M/405M [00:02<00:01, 90.8MB/s]\u001b[A\n",
"Downloading (…)l-00032-of-00033.bin: 62% 252M/405M [00:02<00:01, 90.1MB/s]\u001b[A\n",
"Downloading (…)l-00032-of-00033.bin: 65% 262M/405M [00:02<00:01, 91.8MB/s]\u001b[A\n",
"Downloading (…)l-00032-of-00033.bin: 67% 273M/405M [00:02<00:01, 93.0MB/s]\u001b[A\n",
"Downloading (…)l-00032-of-00033.bin: 70% 283M/405M [00:03<00:01, 93.2MB/s]\u001b[A\n",
"Downloading (…)l-00032-of-00033.bin: 73% 294M/405M [00:03<00:01, 94.4MB/s]\u001b[A\n",
"Downloading (…)l-00032-of-00033.bin: 75% 304M/405M [00:03<00:01, 93.9MB/s]\u001b[A\n",
"Downloading (…)l-00032-of-00033.bin: 78% 315M/405M [00:03<00:00, 92.3MB/s]\u001b[A\n",
"Downloading (…)l-00032-of-00033.bin: 80% 325M/405M [00:03<00:00, 93.9MB/s]\u001b[A\n",
"Downloading (…)l-00032-of-00033.bin: 83% 336M/405M [00:03<00:00, 91.7MB/s]\u001b[A\n",
"Downloading (…)l-00032-of-00033.bin: 85% 346M/405M [00:03<00:00, 89.6MB/s]\u001b[A\n",
"Downloading (…)l-00032-of-00033.bin: 88% 357M/405M [00:03<00:00, 92.0MB/s]\u001b[A\n",
"Downloading (…)l-00032-of-00033.bin: 91% 367M/405M [00:03<00:00, 92.7MB/s]\u001b[A\n",
"Downloading (…)l-00032-of-00033.bin: 93% 377M/405M [00:04<00:00, 93.7MB/s]\u001b[A\n",
"Downloading (…)l-00032-of-00033.bin: 96% 388M/405M [00:04<00:00, 94.6MB/s]\u001b[A\n",
"Downloading (…)l-00032-of-00033.bin: 100% 405M/405M [00:04<00:00, 92.0MB/s]\n",
"Downloading shards: 97% 32/33 [01:48<00:03, 3.47s/it]\n",
"Downloading (…)l-00033-of-00033.bin: 0% 0.00/524M [00:00<?, ?B/s]\u001b[A\n",
"Downloading (…)l-00033-of-00033.bin: 2% 10.5M/524M [00:01<00:50, 10.1MB/s]\u001b[A\n",
"Downloading (…)l-00033-of-00033.bin: 4% 21.0M/524M [00:01<00:23, 21.2MB/s]\u001b[A\n",
"Downloading (…)l-00033-of-00033.bin: 8% 41.9M/524M [00:01<00:10, 44.8MB/s]\u001b[A\n",
"Downloading (…)l-00033-of-00033.bin: 10% 52.4M/524M [00:01<00:08, 53.9MB/s]\u001b[A\n",
"Downloading (…)l-00033-of-00033.bin: 12% 62.9M/524M [00:01<00:07, 62.4MB/s]\u001b[A\n",
"Downloading (…)l-00033-of-00033.bin: 14% 73.4M/524M [00:01<00:06, 69.9MB/s]\u001b[A\n",
"Downloading (…)l-00033-of-00033.bin: 16% 83.9M/524M [00:01<00:05, 76.0MB/s]\u001b[A\n",
"Downloading (…)l-00033-of-00033.bin: 18% 94.4M/524M [00:01<00:05, 78.2MB/s]\u001b[A\n",
"Downloading (…)l-00033-of-00033.bin: 20% 105M/524M [00:01<00:05, 82.6MB/s] \u001b[A\n",
"Downloading (…)l-00033-of-00033.bin: 22% 115M/524M [00:02<00:04, 85.7MB/s]\u001b[A\n",
"Downloading (…)l-00033-of-00033.bin: 24% 126M/524M [00:02<00:04, 88.5MB/s]\u001b[A\n",
"Downloading (…)l-00033-of-00033.bin: 26% 136M/524M [00:02<00:04, 90.9MB/s]\u001b[A\n",
"Downloading (…)l-00033-of-00033.bin: 28% 147M/524M [00:02<00:04, 93.0MB/s]\u001b[A\n",
"Downloading (…)l-00033-of-00033.bin: 30% 157M/524M [00:02<00:03, 94.7MB/s]\u001b[A\n",
"Downloading (…)l-00033-of-00033.bin: 32% 168M/524M [00:02<00:03, 95.4MB/s]\u001b[A\n",
"Downloading (…)l-00033-of-00033.bin: 34% 178M/524M [00:02<00:03, 95.0MB/s]\u001b[A\n",
"Downloading (…)l-00033-of-00033.bin: 36% 189M/524M [00:02<00:03, 95.5MB/s]\u001b[A\n",
"Downloading (…)l-00033-of-00033.bin: 38% 199M/524M [00:02<00:03, 96.6MB/s]\u001b[A\n",
"Downloading (…)l-00033-of-00033.bin: 40% 210M/524M [00:03<00:03, 95.4MB/s]\u001b[A\n",
"Downloading (…)l-00033-of-00033.bin: 42% 220M/524M [00:03<00:03, 96.1MB/s]\u001b[A\n",
"Downloading (…)l-00033-of-00033.bin: 44% 231M/524M [00:03<00:03, 96.1MB/s]\u001b[A\n",
"Downloading (…)l-00033-of-00033.bin: 46% 241M/524M [00:03<00:02, 96.8MB/s]\u001b[A\n",
"Downloading (…)l-00033-of-00033.bin: 48% 252M/524M [00:03<00:02, 96.7MB/s]\u001b[A\n",
"Downloading (…)l-00033-of-00033.bin: 50% 262M/524M [00:03<00:02, 92.2MB/s]\u001b[A\n",
"Downloading (…)l-00033-of-00033.bin: 52% 273M/524M [00:03<00:02, 92.0MB/s]\u001b[A\n",
"Downloading (…)l-00033-of-00033.bin: 54% 283M/524M [00:03<00:02, 93.3MB/s]\u001b[A\n",
"Downloading (…)l-00033-of-00033.bin: 56% 294M/524M [00:03<00:02, 94.2MB/s]\u001b[A\n",
"Downloading (…)l-00033-of-00033.bin: 58% 304M/524M [00:04<00:02, 93.4MB/s]\u001b[A\n",
"Downloading (…)l-00033-of-00033.bin: 60% 315M/524M [00:04<00:02, 92.6MB/s]\u001b[A\n",
"Downloading (…)l-00033-of-00033.bin: 62% 325M/524M [00:04<00:02, 92.4MB/s]\u001b[A\n",
"Downloading (…)l-00033-of-00033.bin: 64% 336M/524M [00:04<00:02, 93.5MB/s]\u001b[A\n",
"Downloading (…)l-00033-of-00033.bin: 66% 346M/524M [00:04<00:01, 94.2MB/s]\u001b[A\n",
"Downloading (…)l-00033-of-00033.bin: 68% 357M/524M [00:04<00:01, 94.3MB/s]\u001b[A\n",
"Downloading (…)l-00033-of-00033.bin: 70% 367M/524M [00:04<00:01, 93.8MB/s]\u001b[A\n",
"Downloading (…)l-00033-of-00033.bin: 72% 377M/524M [00:04<00:01, 94.6MB/s]\u001b[A\n",
"Downloading (…)l-00033-of-00033.bin: 74% 388M/524M [00:04<00:01, 92.8MB/s]\u001b[A\n",
"Downloading (…)l-00033-of-00033.bin: 76% 398M/524M [00:05<00:01, 93.5MB/s]\u001b[A\n",
"Downloading (…)l-00033-of-00033.bin: 78% 409M/524M [00:05<00:01, 92.6MB/s]\u001b[A\n",
"Downloading (…)l-00033-of-00033.bin: 80% 419M/524M [00:05<00:01, 93.5MB/s]\u001b[A\n",
"Downloading (…)l-00033-of-00033.bin: 82% 430M/524M [00:05<00:00, 94.4MB/s]\u001b[A\n",
"Downloading (…)l-00033-of-00033.bin: 84% 440M/524M [00:05<00:00, 94.7MB/s]\u001b[A\n",
"Downloading (…)l-00033-of-00033.bin: 86% 451M/524M [00:05<00:00, 94.4MB/s]\u001b[A\n",
"Downloading (…)l-00033-of-00033.bin: 88% 461M/524M [00:05<00:00, 95.3MB/s]\u001b[A\n",
"Downloading (…)l-00033-of-00033.bin: 90% 472M/524M [00:05<00:00, 94.6MB/s]\u001b[A\n",
"Downloading (…)l-00033-of-00033.bin: 92% 482M/524M [00:05<00:00, 94.3MB/s]\u001b[A\n",
"Downloading (…)l-00033-of-00033.bin: 94% 493M/524M [00:06<00:00, 87.8MB/s]\u001b[A\n",
"Downloading (…)l-00033-of-00033.bin: 96% 503M/524M [00:06<00:00, 89.0MB/s]\u001b[A\n",
"Downloading (…)l-00033-of-00033.bin: 98% 514M/524M [00:06<00:00, 91.8MB/s]\u001b[A\n",
"Downloading (…)l-00033-of-00033.bin: 100% 524M/524M [00:06<00:00, 81.3MB/s]\n",
"Downloading shards: 100% 33/33 [01:55<00:00, 3.49s/it]\n",
"Loading checkpoint shards: 100% 33/33 [00:14<00:00, 2.30it/s]\n",
"Downloading (…)neration_config.json: 100% 124/124 [00:00<00:00, 18.4kB/s]\n",
"Extended vocabulary size: 49954\n",
"Loading LoRA for 7B model\n",
"Downloading (…)/adapter_config.json: 100% 472/472 [00:00<00:00, 166kB/s]\n",
"Downloading adapter_model.bin: 100% 858M/858M [00:08<00:00, 103MB/s]\n",
"Peft version: 0.2.0\n",
"Merging model\n",
"Saving shard 1 of 1 into 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": "8da3382c-6bff-4030-905b-bb4f622766d7"
},
"execution_count": 4,
"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 -DNDEBUG -std=c11 -fPIC -Wall -Wextra -Wpedantic -Wcast-qual -Wdouble-promotion -Wshadow -Wstrict-prototypes -Wpointer-arith -Wno-unused-function -pthread -march=native -mtune=native\n",
"I CXXFLAGS: -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-multichar -pthread -march=native -mtune=native\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 -DNDEBUG -std=c11 -fPIC -Wall -Wextra -Wpedantic -Wcast-qual -Wdouble-promotion -Wshadow -Wstrict-prototypes -Wpointer-arith -Wno-unused-function -pthread -march=native -mtune=native -c ggml.c -o ggml.o\n",
"g++ -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-multichar -pthread -march=native -mtune=native -c llama.cpp -o llama.o\n",
"In file included from \u001b[01m\u001b[Kllama.cpp:6\u001b[m\u001b[K:\n",
"\u001b[01m\u001b[Kllama_util.h:60:2:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[Kextra \u001b[01m\u001b[K;\u001b[m\u001b[K [\u001b[01;35m\u001b[K-Wpedantic\u001b[m\u001b[K]\n",
" 60 | }\u001b[01;35m\u001b[K;\u001b[m\u001b[K\n",
" | \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n",
"g++ -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-multichar -pthread -march=native -mtune=native -c examples/common.cpp -o common.o\n",
"g++ -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-multichar -pthread -march=native -mtune=native examples/main/main.cpp ggml.o llama.o common.o -o main \n",
"\n",
"==== Run ./main -h for help. ====\n",
"\n",
"g++ -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-multichar -pthread -march=native -mtune=native examples/quantize/quantize.cpp ggml.o llama.o -o quantize \n",
"g++ -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-multichar -pthread -march=native -mtune=native examples/perplexity/perplexity.cpp ggml.o llama.o common.o -o perplexity \n",
"g++ -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-multichar -pthread -march=native -mtune=native examples/embedding/embedding.cpp ggml.o llama.o common.o -o embedding \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模型提示:\n",
"- tokenizer可以直接用7B的,13B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": "09ba7058-e2fb-4ae1-8539-62228df6ea09"
},
"execution_count": 6,
"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": "356f9e70-d05d-42d3-ed8c-fc052e11a855"
},
"execution_count": 7,
"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...\n",
"[2/291] Writing tensor norm.weight, size 4096...\n",
"[3/291] Writing tensor output.weight, size 49954 x 4096...\n",
"[4/291] Writing tensor layers.0.attention.wq.weight, size 4096 x 4096...\n",
"[5/291] Writing tensor layers.0.attention.wk.weight, size 4096 x 4096...\n",
"[6/291] Writing tensor layers.0.attention.wv.weight, size 4096 x 4096...\n",
"[7/291] Writing tensor layers.0.attention.wo.weight, size 4096 x 4096...\n",
"[8/291] Writing tensor layers.0.attention_norm.weight, size 4096...\n",
"[9/291] Writing tensor layers.0.feed_forward.w1.weight, size 11008 x 4096...\n",
"[10/291] Writing tensor layers.0.feed_forward.w2.weight, size 4096 x 11008...\n",
"[11/291] Writing tensor layers.0.feed_forward.w3.weight, size 11008 x 4096...\n",
"[12/291] Writing tensor layers.0.ffn_norm.weight, size 4096...\n",
"[13/291] Writing tensor layers.1.attention.wq.weight, size 4096 x 4096...\n",
"[14/291] Writing tensor layers.1.attention.wk.weight, size 4096 x 4096...\n",
"[15/291] Writing tensor layers.1.attention.wv.weight, size 4096 x 4096...\n",
"[16/291] Writing tensor layers.1.attention.wo.weight, size 4096 x 4096...\n",
"[17/291] Writing tensor layers.1.attention_norm.weight, size 4096...\n",
"[18/291] Writing tensor layers.1.feed_forward.w1.weight, size 11008 x 4096...\n",
"[19/291] Writing tensor layers.1.feed_forward.w2.weight, size 4096 x 11008...\n",
"[20/291] Writing tensor layers.1.feed_forward.w3.weight, size 11008 x 4096...\n",
"[21/291] Writing tensor layers.1.ffn_norm.weight, size 4096...\n",
"[22/291] Writing tensor layers.2.attention.wq.weight, size 4096 x 4096...\n",
"[23/291] Writing tensor layers.2.attention.wk.weight, size 4096 x 4096...\n",
"[24/291] Writing tensor layers.2.attention.wv.weight, size 4096 x 4096...\n",
"[25/291] Writing tensor layers.2.attention.wo.weight, size 4096 x 4096...\n",
"[26/291] Writing tensor layers.2.attention_norm.weight, size 4096...\n",
"[27/291] Writing tensor layers.2.feed_forward.w1.weight, size 11008 x 4096...\n",
"[28/291] Writing tensor layers.2.feed_forward.w2.weight, size 4096 x 11008...\n",
"[29/291] Writing tensor layers.2.feed_forward.w3.weight, size 11008 x 4096...\n",
"[30/291] Writing tensor layers.2.ffn_norm.weight, size 4096...\n",
"[31/291] Writing tensor layers.3.attention.wq.weight, size 4096 x 4096...\n",
"[32/291] Writing tensor layers.3.attention.wk.weight, size 4096 x 4096...\n",
"[33/291] Writing tensor layers.3.attention.wv.weight, size 4096 x 4096...\n",
"[34/291] Writing tensor layers.3.attention.wo.weight, size 4096 x 4096...\n",
"[35/291] Writing tensor layers.3.attention_norm.weight, size 4096...\n",
"[36/291] Writing tensor layers.3.feed_forward.w1.weight, size 11008 x 4096...\n",
"[37/291] Writing tensor layers.3.feed_forward.w2.weight, size 4096 x 11008...\n",
"[38/291] Writing tensor layers.3.feed_forward.w3.weight, size 11008 x 4096...\n",
"[39/291] Writing tensor layers.3.ffn_norm.weight, size 4096...\n",
"[40/291] Writing tensor layers.4.attention.wq.weight, size 4096 x 4096...\n",
"[41/291] Writing tensor layers.4.attention.wk.weight, size 4096 x 4096...\n",
"[42/291] Writing tensor layers.4.attention.wv.weight, size 4096 x 4096...\n",
"[43/291] Writing tensor layers.4.attention.wo.weight, size 4096 x 4096...\n",
"[44/291] Writing tensor layers.4.attention_norm.weight, size 4096...\n",
"[45/291] Writing tensor layers.4.feed_forward.w1.weight, size 11008 x 4096...\n",
"[46/291] Writing tensor layers.4.feed_forward.w2.weight, size 4096 x 11008...\n",
"[47/291] Writing tensor layers.4.feed_forward.w3.weight, size 11008 x 4096...\n",
"[48/291] Writing tensor layers.4.ffn_norm.weight, size 4096...\n",
"[49/291] Writing tensor layers.5.attention.wq.weight, size 4096 x 4096...\n",
"[50/291] Writing tensor layers.5.attention.wk.weight, size 4096 x 4096...\n",
"[51/291] Writing tensor layers.5.attention.wv.weight, size 4096 x 4096...\n",
"[52/291] Writing tensor layers.5.attention.wo.weight, size 4096 x 4096...\n",
"[53/291] Writing tensor layers.5.attention_norm.weight, size 4096...\n",
"[54/291] Writing tensor layers.5.feed_forward.w1.weight, size 11008 x 4096...\n",
"[55/291] Writing tensor layers.5.feed_forward.w2.weight, size 4096 x 11008...\n",
"[56/291] Writing tensor layers.5.feed_forward.w3.weight, size 11008 x 4096...\n",
"[57/291] Writing tensor layers.5.ffn_norm.weight, size 4096...\n",
"[58/291] Writing tensor layers.6.attention.wq.weight, size 4096 x 4096...\n",
"[59/291] Writing tensor layers.6.attention.wk.weight, size 4096 x 4096...\n",
"[60/291] Writing tensor layers.6.attention.wv.weight, size 4096 x 4096...\n",
"[61/291] Writing tensor layers.6.attention.wo.weight, size 4096 x 4096...\n",
"[62/291] Writing tensor layers.6.attention_norm.weight, size 4096...\n",
"[63/291] Writing tensor layers.6.feed_forward.w1.weight, size 11008 x 4096...\n",
"[64/291] Writing tensor layers.6.feed_forward.w2.weight, size 4096 x 11008...\n",
"[65/291] Writing tensor layers.6.feed_forward.w3.weight, size 11008 x 4096...\n",
"[66/291] Writing tensor layers.6.ffn_norm.weight, size 4096...\n",
"[67/291] Writing tensor layers.7.attention.wq.weight, size 4096 x 4096...\n",
"[68/291] Writing tensor layers.7.attention.wk.weight, size 4096 x 4096...\n",
"[69/291] Writing tensor layers.7.attention.wv.weight, size 4096 x 4096...\n",
"[70/291] Writing tensor layers.7.attention.wo.weight, size 4096 x 4096...\n",
"[71/291] Writing tensor layers.7.attention_norm.weight, size 4096...\n",
"[72/291] Writing tensor layers.7.feed_forward.w1.weight, size 11008 x 4096...\n",
"[73/291] Writing tensor layers.7.feed_forward.w2.weight, size 4096 x 11008...\n",
"[74/291] Writing tensor layers.7.feed_forward.w3.weight, size 11008 x 4096...\n",
"[75/291] Writing tensor layers.7.ffn_norm.weight, size 4096...\n",
"[76/291] Writing tensor layers.8.attention.wq.weight, size 4096 x 4096...\n",
"[77/291] Writing tensor layers.8.attention.wk.weight, size 4096 x 4096...\n",
"[78/291] Writing tensor layers.8.attention.wv.weight, size 4096 x 4096...\n",
"[79/291] Writing tensor layers.8.attention.wo.weight, size 4096 x 4096...\n",
"[80/291] Writing tensor layers.8.attention_norm.weight, size 4096...\n",
"[81/291] Writing tensor layers.8.feed_forward.w1.weight, size 11008 x 4096...\n",
"[82/291] Writing tensor layers.8.feed_forward.w2.weight, size 4096 x 11008...\n",
"[83/291] Writing tensor layers.8.feed_forward.w3.weight, size 11008 x 4096...\n",
"[84/291] Writing tensor layers.8.ffn_norm.weight, size 4096...\n",
"[85/291] Writing tensor layers.9.attention.wq.weight, size 4096 x 4096...\n",
"[86/291] Writing tensor layers.9.attention.wk.weight, size 4096 x 4096...\n",
"[87/291] Writing tensor layers.9.attention.wv.weight, size 4096 x 4096...\n",
"[88/291] Writing tensor layers.9.attention.wo.weight, size 4096 x 4096...\n",
"[89/291] Writing tensor layers.9.attention_norm.weight, size 4096...\n",
"[90/291] Writing tensor layers.9.feed_forward.w1.weight, size 11008 x 4096...\n",
"[91/291] Writing tensor layers.9.feed_forward.w2.weight, size 4096 x 11008...\n",
"[92/291] Writing tensor layers.9.feed_forward.w3.weight, size 11008 x 4096...\n",
"[93/291] Writing tensor layers.9.ffn_norm.weight, size 4096...\n",
"[94/291] Writing tensor layers.10.attention.wq.weight, size 4096 x 4096...\n",
"[95/291] Writing tensor layers.10.attention.wk.weight, size 4096 x 4096...\n",
"[96/291] Writing tensor layers.10.attention.wv.weight, size 4096 x 4096...\n",
"[97/291] Writing tensor layers.10.attention.wo.weight, size 4096 x 4096...\n",
"[98/291] Writing tensor layers.10.attention_norm.weight, size 4096...\n",
"[99/291] Writing tensor layers.10.feed_forward.w1.weight, size 11008 x 4096...\n",
"[100/291] Writing tensor layers.10.feed_forward.w2.weight, size 4096 x 11008...\n",
"[101/291] Writing tensor layers.10.feed_forward.w3.weight, size 11008 x 4096...\n",
"[102/291] Writing tensor layers.10.ffn_norm.weight, size 4096...\n",
"[103/291] Writing tensor layers.11.attention.wq.weight, size 4096 x 4096...\n",
"[104/291] Writing tensor layers.11.attention.wk.weight, size 4096 x 4096...\n",
"[105/291] Writing tensor layers.11.attention.wv.weight, size 4096 x 4096...\n",
"[106/291] Writing tensor layers.11.attention.wo.weight, size 4096 x 4096...\n",
"[107/291] Writing tensor layers.11.attention_norm.weight, size 4096...\n",
"[108/291] Writing tensor layers.11.feed_forward.w1.weight, size 11008 x 4096...\n",
"[109/291] Writing tensor layers.11.feed_forward.w2.weight, size 4096 x 11008...\n",
"[110/291] Writing tensor layers.11.feed_forward.w3.weight, size 11008 x 4096...\n",
"[111/291] Writing tensor layers.11.ffn_norm.weight, size 4096...\n",
"[112/291] Writing tensor layers.12.attention.wq.weight, size 4096 x 4096...\n",
"[113/291] Writing tensor layers.12.attention.wk.weight, size 4096 x 4096...\n",
"[114/291] Writing tensor layers.12.attention.wv.weight, size 4096 x 4096...\n",
"[115/291] Writing tensor layers.12.attention.wo.weight, size 4096 x 4096...\n",
"[116/291] Writing tensor layers.12.attention_norm.weight, size 4096...\n",
"[117/291] Writing tensor layers.12.feed_forward.w1.weight, size 11008 x 4096...\n",
"[118/291] Writing tensor layers.12.feed_forward.w2.weight, size 4096 x 11008...\n",
"[119/291] Writing tensor layers.12.feed_forward.w3.weight, size 11008 x 4096...\n",
"[120/291] Writing tensor layers.12.ffn_norm.weight, size 4096...\n",
"[121/291] Writing tensor layers.13.attention.wq.weight, size 4096 x 4096...\n",
"[122/291] Writing tensor layers.13.attention.wk.weight, size 4096 x 4096...\n",
"[123/291] Writing tensor layers.13.attention.wv.weight, size 4096 x 4096...\n",
"[124/291] Writing tensor layers.13.attention.wo.weight, size 4096 x 4096...\n",
"[125/291] Writing tensor layers.13.attention_norm.weight, size 4096...\n",
"[126/291] Writing tensor layers.13.feed_forward.w1.weight, size 11008 x 4096...\n",
"[127/291] Writing tensor layers.13.feed_forward.w2.weight, size 4096 x 11008...\n",
"[128/291] Writing tensor layers.13.feed_forward.w3.weight, size 11008 x 4096...\n",
"[129/291] Writing tensor layers.13.ffn_norm.weight, size 4096...\n",
"[130/291] Writing tensor layers.14.attention.wq.weight, size 4096 x 4096...\n",
"[131/291] Writing tensor layers.14.attention.wk.weight, size 4096 x 4096...\n",
"[132/291] Writing tensor layers.14.attention.wv.weight, size 4096 x 4096...\n",
"[133/291] Writing tensor layers.14.attention.wo.weight, size 4096 x 4096...\n",
"[134/291] Writing tensor layers.14.attention_norm.weight, size 4096...\n",
"[135/291] Writing tensor layers.14.feed_forward.w1.weight, size 11008 x 4096...\n",
"[136/291] Writing tensor layers.14.feed_forward.w2.weight, size 4096 x 11008...\n",
"[137/291] Writing tensor layers.14.feed_forward.w3.weight, size 11008 x 4096...\n",
"[138/291] Writing tensor layers.14.ffn_norm.weight, size 4096...\n",
"[139/291] Writing tensor layers.15.attention.wq.weight, size 4096 x 4096...\n",
"[140/291] Writing tensor layers.15.attention.wk.weight, size 4096 x 4096...\n",
"[141/291] Writing tensor layers.15.attention.wv.weight, size 4096 x 4096...\n",
"[142/291] Writing tensor layers.15.attention.wo.weight, size 4096 x 4096...\n",
"[143/291] Writing tensor layers.15.attention_norm.weight, size 4096...\n",
"[144/291] Writing tensor layers.15.feed_forward.w1.weight, size 11008 x 4096...\n",
"[145/291] Writing tensor layers.15.feed_forward.w2.weight, size 4096 x 11008...\n",
"[146/291] Writing tensor layers.15.feed_forward.w3.weight, size 11008 x 4096...\n",
"[147/291] Writing tensor layers.15.ffn_norm.weight, size 4096...\n",
"[148/291] Writing tensor layers.16.attention.wq.weight, size 4096 x 4096...\n",
"[149/291] Writing tensor layers.16.attention.wk.weight, size 4096 x 4096...\n",
"[150/291] Writing tensor layers.16.attention.wv.weight, size 4096 x 4096...\n",
"[151/291] Writing tensor layers.16.attention.wo.weight, size 4096 x 4096...\n",
"[152/291] Writing tensor layers.16.attention_norm.weight, size 4096...\n",
"[153/291] Writing tensor layers.16.feed_forward.w1.weight, size 11008 x 4096...\n",
"[154/291] Writing tensor layers.16.feed_forward.w2.weight, size 4096 x 11008...\n",
"[155/291] Writing tensor layers.16.feed_forward.w3.weight, size 11008 x 4096...\n",
"[156/291] Writing tensor layers.16.ffn_norm.weight, size 4096...\n",
"[157/291] Writing tensor layers.17.attention.wq.weight, size 4096 x 4096...\n",
"[158/291] Writing tensor layers.17.attention.wk.weight, size 4096 x 4096...\n",
"[159/291] Writing tensor layers.17.attention.wv.weight, size 4096 x 4096...\n",
"[160/291] Writing tensor layers.17.attention.wo.weight, size 4096 x 4096...\n",
"[161/291] Writing tensor layers.17.attention_norm.weight, size 4096...\n",
"[162/291] Writing tensor layers.17.feed_forward.w1.weight, size 11008 x 4096...\n",
"[163/291] Writing tensor layers.17.feed_forward.w2.weight, size 4096 x 11008...\n",
"[164/291] Writing tensor layers.17.feed_forward.w3.weight, size 11008 x 4096...\n",
"[165/291] Writing tensor layers.17.ffn_norm.weight, size 4096...\n",
"[166/291] Writing tensor layers.18.attention.wq.weight, size 4096 x 4096...\n",
"[167/291] Writing tensor layers.18.attention.wk.weight, size 4096 x 4096...\n",
"[168/291] Writing tensor layers.18.attention.wv.weight, size 4096 x 4096...\n",
"[169/291] Writing tensor layers.18.attention.wo.weight, size 4096 x 4096...\n",
"[170/291] Writing tensor layers.18.attention_norm.weight, size 4096...\n",
"[171/291] Writing tensor layers.18.feed_forward.w1.weight, size 11008 x 4096...\n",
"[172/291] Writing tensor layers.18.feed_forward.w2.weight, size 4096 x 11008...\n",
"[173/291] Writing tensor layers.18.feed_forward.w3.weight, size 11008 x 4096...\n",
"[174/291] Writing tensor layers.18.ffn_norm.weight, size 4096...\n",
"[175/291] Writing tensor layers.19.attention.wq.weight, size 4096 x 4096...\n",
"[176/291] Writing tensor layers.19.attention.wk.weight, size 4096 x 4096...\n",
"[177/291] Writing tensor layers.19.attention.wv.weight, size 4096 x 4096...\n",
"[178/291] Writing tensor layers.19.attention.wo.weight, size 4096 x 4096...\n",
"[179/291] Writing tensor layers.19.attention_norm.weight, size 4096...\n",
"[180/291] Writing tensor layers.19.feed_forward.w1.weight, size 11008 x 4096...\n",
"[181/291] Writing tensor layers.19.feed_forward.w2.weight, size 4096 x 11008...\n",
"[182/291] Writing tensor layers.19.feed_forward.w3.weight, size 11008 x 4096...\n",
"[183/291] Writing tensor layers.19.ffn_norm.weight, size 4096...\n",
"[184/291] Writing tensor layers.20.attention.wq.weight, size 4096 x 4096...\n",
"[185/291] Writing tensor layers.20.attention.wk.weight, size 4096 x 4096...\n",
"[186/291] Writing tensor layers.20.attention.wv.weight, size 4096 x 4096...\n",
"[187/291] Writing tensor layers.20.attention.wo.weight, size 4096 x 4096...\n",
"[188/291] Writing tensor layers.20.attention_norm.weight, size 4096...\n",
"[189/291] Writing tensor layers.20.feed_forward.w1.weight, size 11008 x 4096...\n",
"[190/291] Writing tensor layers.20.feed_forward.w2.weight, size 4096 x 11008...\n",
"[191/291] Writing tensor layers.20.feed_forward.w3.weight, size 11008 x 4096...\n",
"[192/291] Writing tensor layers.20.ffn_norm.weight, size 4096...\n",
"[193/291] Writing tensor layers.21.attention.wq.weight, size 4096 x 4096...\n",
"[194/291] Writing tensor layers.21.attention.wk.weight, size 4096 x 4096...\n",
"[195/291] Writing tensor layers.21.attention.wv.weight, size 4096 x 4096...\n",
"[196/291] Writing tensor layers.21.attention.wo.weight, size 4096 x 4096...\n",
"[197/291] Writing tensor layers.21.attention_norm.weight, size 4096...\n",
"[198/291] Writing tensor layers.21.feed_forward.w1.weight, size 11008 x 4096...\n",
"[199/291] Writing tensor layers.21.feed_forward.w2.weight, size 4096 x 11008...\n",
"[200/291] Writing tensor layers.21.feed_forward.w3.weight, size 11008 x 4096...\n",
"[201/291] Writing tensor layers.21.ffn_norm.weight, size 4096...\n",
"[202/291] Writing tensor layers.22.attention.wq.weight, size 4096 x 4096...\n",
"[203/291] Writing tensor layers.22.attention.wk.weight, size 4096 x 4096...\n",
"[204/291] Writing tensor layers.22.attention.wv.weight, size 4096 x 4096...\n",
"[205/291] Writing tensor layers.22.attention.wo.weight, size 4096 x 4096...\n",
"[206/291] Writing tensor layers.22.attention_norm.weight, size 4096...\n",
"[207/291] Writing tensor layers.22.feed_forward.w1.weight, size 11008 x 4096...\n",
"[208/291] Writing tensor layers.22.feed_forward.w2.weight, size 4096 x 11008...\n",
"[209/291] Writing tensor layers.22.feed_forward.w3.weight, size 11008 x 4096...\n",
"[210/291] Writing tensor layers.22.ffn_norm.weight, size 4096...\n",
"[211/291] Writing tensor layers.23.attention.wq.weight, size 4096 x 4096...\n",
"[212/291] Writing tensor layers.23.attention.wk.weight, size 4096 x 4096...\n",
"[213/291] Writing tensor layers.23.attention.wv.weight, size 4096 x 4096...\n",
"[214/291] Writing tensor layers.23.attention.wo.weight, size 4096 x 4096...\n",
"[215/291] Writing tensor layers.23.attention_norm.weight, size 4096...\n",
"[216/291] Writing tensor layers.23.feed_forward.w1.weight, size 11008 x 4096...\n",
"[217/291] Writing tensor layers.23.feed_forward.w2.weight, size 4096 x 11008...\n",
"[218/291] Writing tensor layers.23.feed_forward.w3.weight, size 11008 x 4096...\n",
"[219/291] Writing tensor layers.23.ffn_norm.weight, size 4096...\n",
"[220/291] Writing tensor layers.24.attention.wq.weight, size 4096 x 4096...\n",
"[221/291] Writing tensor layers.24.attention.wk.weight, size 4096 x 4096...\n",
"[222/291] Writing tensor layers.24.attention.wv.weight, size 4096 x 4096...\n",
"[223/291] Writing tensor layers.24.attention.wo.weight, size 4096 x 4096...\n",
"[224/291] Writing tensor layers.24.attention_norm.weight, size 4096...\n",
"[225/291] Writing tensor layers.24.feed_forward.w1.weight, size 11008 x 4096...\n",
"[226/291] Writing tensor layers.24.feed_forward.w2.weight, size 4096 x 11008...\n",
"[227/291] Writing tensor layers.24.feed_forward.w3.weight, size 11008 x 4096...\n",
"[228/291] Writing tensor layers.24.ffn_norm.weight, size 4096...\n",
"[229/291] Writing tensor layers.25.attention.wq.weight, size 4096 x 4096...\n",
"[230/291] Writing tensor layers.25.attention.wk.weight, size 4096 x 4096...\n",
"[231/291] Writing tensor layers.25.attention.wv.weight, size 4096 x 4096...\n",
"[232/291] Writing tensor layers.25.attention.wo.weight, size 4096 x 4096...\n",
"[233/291] Writing tensor layers.25.attention_norm.weight, size 4096...\n",
"[234/291] Writing tensor layers.25.feed_forward.w1.weight, size 11008 x 4096...\n",
"[235/291] Writing tensor layers.25.feed_forward.w2.weight, size 4096 x 11008...\n",
"[236/291] Writing tensor layers.25.feed_forward.w3.weight, size 11008 x 4096...\n",
"[237/291] Writing tensor layers.25.ffn_norm.weight, size 4096...\n",
"[238/291] Writing tensor layers.26.attention.wq.weight, size 4096 x 4096...\n",
"[239/291] Writing tensor layers.26.attention.wk.weight, size 4096 x 4096...\n",
"[240/291] Writing tensor layers.26.attention.wv.weight, size 4096 x 4096...\n",
"[241/291] Writing tensor layers.26.attention.wo.weight, size 4096 x 4096...\n",
"[242/291] Writing tensor layers.26.attention_norm.weight, size 4096...\n",
"[243/291] Writing tensor layers.26.feed_forward.w1.weight, size 11008 x 4096...\n",
"[244/291] Writing tensor layers.26.feed_forward.w2.weight, size 4096 x 11008...\n",
"[245/291] Writing tensor layers.26.feed_forward.w3.weight, size 11008 x 4096...\n",
"[246/291] Writing tensor layers.26.ffn_norm.weight, size 4096...\n",
"[247/291] Writing tensor layers.27.attention.wq.weight, size 4096 x 4096...\n",
"[248/291] Writing tensor layers.27.attention.wk.weight, size 4096 x 4096...\n",
"[249/291] Writing tensor layers.27.attention.wv.weight, size 4096 x 4096...\n",
"[250/291] Writing tensor layers.27.attention.wo.weight, size 4096 x 4096...\n",
"[251/291] Writing tensor layers.27.attention_norm.weight, size 4096...\n",
"[252/291] Writing tensor layers.27.feed_forward.w1.weight, size 11008 x 4096...\n",
"[253/291] Writing tensor layers.27.feed_forward.w2.weight, size 4096 x 11008...\n",
"[254/291] Writing tensor layers.27.feed_forward.w3.weight, size 11008 x 4096...\n",
"[255/291] Writing tensor layers.27.ffn_norm.weight, size 4096...\n",
"[256/291] Writing tensor layers.28.attention.wq.weight, size 4096 x 4096...\n",
"[257/291] Writing tensor layers.28.attention.wk.weight, size 4096 x 4096...\n",
"[258/291] Writing tensor layers.28.attention.wv.weight, size 4096 x 4096...\n",
"[259/291] Writing tensor layers.28.attention.wo.weight, size 4096 x 4096...\n",
"[260/291] Writing tensor layers.28.attention_norm.weight, size 4096...\n",
"[261/291] Writing tensor layers.28.feed_forward.w1.weight, size 11008 x 4096...\n",
"[262/291] Writing tensor layers.28.feed_forward.w2.weight, size 4096 x 11008...\n",
"[263/291] Writing tensor layers.28.feed_forward.w3.weight, size 11008 x 4096...\n",
"[264/291] Writing tensor layers.28.ffn_norm.weight, size 4096...\n",
"[265/291] Writing tensor layers.29.attention.wq.weight, size 4096 x 4096...\n",
"[266/291] Writing tensor layers.29.attention.wk.weight, size 4096 x 4096...\n",
"[267/291] Writing tensor layers.29.attention.wv.weight, size 4096 x 4096...\n",
"[268/291] Writing tensor layers.29.attention.wo.weight, size 4096 x 4096...\n",
"[269/291] Writing tensor layers.29.attention_norm.weight, size 4096...\n",
"[270/291] Writing tensor layers.29.feed_forward.w1.weight, size 11008 x 4096...\n",
"[271/291] Writing tensor layers.29.feed_forward.w2.weight, size 4096 x 11008...\n",
"[272/291] Writing tensor layers.29.feed_forward.w3.weight, size 11008 x 4096...\n",
"[273/291] Writing tensor layers.29.ffn_norm.weight, size 4096...\n",
"[274/291] Writing tensor layers.30.attention.wq.weight, size 4096 x 4096...\n",
"[275/291] Writing tensor layers.30.attention.wk.weight, size 4096 x 4096...\n",
"[276/291] Writing tensor layers.30.attention.wv.weight, size 4096 x 4096...\n",
"[277/291] Writing tensor layers.30.attention.wo.weight, size 4096 x 4096...\n",
"[278/291] Writing tensor layers.30.attention_norm.weight, size 4096...\n",
"[279/291] Writing tensor layers.30.feed_forward.w1.weight, size 11008 x 4096...\n",
"[280/291] Writing tensor layers.30.feed_forward.w2.weight, size 4096 x 11008...\n",
"[281/291] Writing tensor layers.30.feed_forward.w3.weight, size 11008 x 4096...\n",
"[282/291] Writing tensor layers.30.ffn_norm.weight, size 4096...\n",
"[283/291] Writing tensor layers.31.attention.wq.weight, size 4096 x 4096...\n",
"[284/291] Writing tensor layers.31.attention.wk.weight, size 4096 x 4096...\n",
"[285/291] Writing tensor layers.31.attention.wv.weight, size 4096 x 4096...\n",
"[286/291] Writing tensor layers.31.attention.wo.weight, size 4096 x 4096...\n",
"[287/291] Writing tensor layers.31.attention_norm.weight, size 4096...\n",
"[288/291] Writing tensor layers.31.feed_forward.w1.weight, size 11008 x 4096...\n",
"[289/291] Writing tensor layers.31.feed_forward.w2.weight, size 4096 x 11008...\n",
"[290/291] Writing tensor layers.31.feed_forward.w3.weight, size 11008 x 4096...\n",
"[291/291] Writing tensor layers.31.ffn_norm.weight, size 4096...\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。"
],
"metadata": {
"id": "hEZEJAVYCHkc"
}
},
{
"cell_type": "code",
"source": [
"!cd llama.cpp && ./quantize ./zh-models/7B/ggml-model-f16.bin ./zh-models/7B/ggml-model-q4_0.bin 2"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "2xyais7OUVDI",
"outputId": "99b4154e-1370-4240-c06b-69ff2f49ee37"
},
"execution_count": 8,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"llama.cpp: loading model from ./zh-models/7B/ggml-model-f16.bin\n",
"llama.cpp: saving model to ./zh-models/7B/ggml-model-q4_0.bin\n",
"[1/291] tok_embeddings.weight - [4096 x 49954], type = f16, quantizing .. size = 390.27 MB -> 121.96 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \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 -> 121.96 MB | hist: 0.000 0.022 0.019 0.033 0.052 0.077 0.104 0.126 0.134 0.126 0.104 0.077 0.052 0.033 0.019 0.022 \n",
"[4/291] layers.0.attention.wq.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.021 0.016 0.028 0.046 0.071 0.103 0.137 0.158 0.137 0.103 0.071 0.046 0.028 0.016 0.021 \n",
"[5/291] layers.0.attention.wk.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.021 0.016 0.027 0.045 0.071 0.104 0.138 0.158 0.139 0.104 0.071 0.045 0.027 0.016 0.021 \n",
"[6/291] layers.0.attention.wv.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.018 0.032 0.051 0.076 0.103 0.128 0.141 0.128 0.103 0.075 0.051 0.032 0.019 0.022 \n",
"[7/291] layers.0.attention.wo.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.021 0.016 0.028 0.046 0.072 0.105 0.136 0.151 0.136 0.105 0.072 0.046 0.028 0.016 0.021 \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 -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[10/291] layers.0.feed_forward.w2.weight - [11008 x 4096], type = f16, quantizing .. size = 86.00 MB -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.052 0.077 0.104 0.126 0.134 0.126 0.104 0.077 0.052 0.033 0.019 0.022 \n",
"[11/291] layers.0.feed_forward.w3.weight - [4096 x 11008], type = f16, quantizing .. size = 86.00 MB -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.052 0.077 0.104 0.126 0.134 0.125 0.104 0.077 0.052 0.033 0.019 0.022 \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 -> 10.00 MB | hist: 0.000 0.022 0.019 0.032 0.051 0.077 0.104 0.127 0.137 0.127 0.104 0.077 0.051 0.032 0.019 0.022 \n",
"[14/291] layers.1.attention.wk.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.021 0.018 0.032 0.051 0.076 0.104 0.128 0.138 0.128 0.104 0.077 0.051 0.032 0.018 0.022 \n",
"[15/291] layers.1.attention.wv.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.018 0.031 0.051 0.076 0.104 0.129 0.139 0.129 0.104 0.076 0.051 0.031 0.018 0.021 \n",
"[16/291] layers.1.attention.wo.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.021 0.016 0.028 0.046 0.071 0.104 0.137 0.154 0.137 0.104 0.071 0.046 0.028 0.016 0.021 \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 -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[19/291] layers.1.feed_forward.w2.weight - [11008 x 4096], type = f16, quantizing .. size = 86.00 MB -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[20/291] layers.1.feed_forward.w3.weight - [4096 x 11008], type = f16, quantizing .. size = 86.00 MB -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \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 -> 10.00 MB | hist: 0.000 0.022 0.019 0.032 0.052 0.077 0.104 0.126 0.135 0.126 0.104 0.077 0.052 0.033 0.019 0.022 \n",
"[23/291] layers.2.attention.wk.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.032 0.051 0.076 0.104 0.127 0.137 0.127 0.104 0.077 0.051 0.032 0.019 0.022 \n",
"[24/291] layers.2.attention.wv.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.052 0.077 0.104 0.125 0.136 0.125 0.104 0.077 0.052 0.033 0.019 0.022 \n",
"[25/291] layers.2.attention.wo.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.032 0.052 0.077 0.104 0.126 0.135 0.126 0.104 0.077 0.052 0.032 0.019 0.022 \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 -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[28/291] layers.2.feed_forward.w2.weight - [11008 x 4096], type = f16, quantizing .. size = 86.00 MB -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[29/291] layers.2.feed_forward.w3.weight - [4096 x 11008], type = f16, quantizing .. size = 86.00 MB -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \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 -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.052 0.077 0.104 0.126 0.135 0.126 0.104 0.077 0.052 0.032 0.019 0.022 \n",
"[32/291] layers.3.attention.wk.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.032 0.052 0.077 0.104 0.126 0.136 0.126 0.104 0.077 0.052 0.032 0.019 0.022 \n",
"[33/291] layers.3.attention.wv.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.052 0.077 0.104 0.125 0.135 0.126 0.104 0.077 0.052 0.033 0.019 0.022 \n",
"[34/291] layers.3.attention.wo.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \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 -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[37/291] layers.3.feed_forward.w2.weight - [11008 x 4096], type = f16, quantizing .. size = 86.00 MB -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[38/291] layers.3.feed_forward.w3.weight - [4096 x 11008], type = f16, quantizing .. size = 86.00 MB -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \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 -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.052 0.077 0.104 0.126 0.135 0.126 0.104 0.077 0.052 0.033 0.019 0.022 \n",
"[41/291] layers.4.attention.wk.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.032 0.052 0.077 0.104 0.126 0.135 0.126 0.104 0.077 0.052 0.032 0.019 0.022 \n",
"[42/291] layers.4.attention.wv.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.077 0.104 0.125 0.135 0.125 0.104 0.077 0.052 0.033 0.019 0.022 \n",
"[43/291] layers.4.attention.wo.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.052 0.078 0.104 0.125 0.134 0.125 0.104 0.077 0.053 0.033 0.019 0.022 \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 -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[46/291] layers.4.feed_forward.w2.weight - [11008 x 4096], type = f16, quantizing .. size = 86.00 MB -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[47/291] layers.4.feed_forward.w3.weight - [4096 x 11008], type = f16, quantizing .. size = 86.00 MB -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \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 -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.077 0.104 0.125 0.134 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[50/291] layers.5.attention.wk.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.052 0.077 0.104 0.126 0.134 0.126 0.104 0.077 0.052 0.033 0.019 0.022 \n",
"[51/291] layers.5.attention.wv.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.052 0.077 0.104 0.125 0.135 0.125 0.104 0.077 0.052 0.033 0.019 0.022 \n",
"[52/291] layers.5.attention.wo.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.132 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \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 -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[55/291] layers.5.feed_forward.w2.weight - [11008 x 4096], type = f16, quantizing .. size = 86.00 MB -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[56/291] layers.5.feed_forward.w3.weight - [4096 x 11008], type = f16, quantizing .. size = 86.00 MB -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \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 -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.134 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[59/291] layers.6.attention.wk.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.052 0.077 0.104 0.125 0.134 0.126 0.104 0.077 0.052 0.033 0.019 0.022 \n",
"[60/291] layers.6.attention.wv.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.077 0.104 0.126 0.134 0.125 0.104 0.077 0.053 0.033 0.019 0.022 \n",
"[61/291] layers.6.attention.wo.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \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 -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[64/291] layers.6.feed_forward.w2.weight - [11008 x 4096], type = f16, quantizing .. size = 86.00 MB -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[65/291] layers.6.feed_forward.w3.weight - [4096 x 11008], type = f16, quantizing .. size = 86.00 MB -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \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 -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.077 0.104 0.125 0.134 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[68/291] layers.7.attention.wk.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.077 0.104 0.126 0.134 0.126 0.104 0.077 0.052 0.033 0.019 0.022 \n",
"[69/291] layers.7.attention.wv.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.052 0.077 0.104 0.125 0.135 0.126 0.104 0.077 0.052 0.033 0.019 0.022 \n",
"[70/291] layers.7.attention.wo.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \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 -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[73/291] layers.7.feed_forward.w2.weight - [11008 x 4096], type = f16, quantizing .. size = 86.00 MB -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.134 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[74/291] layers.7.feed_forward.w3.weight - [4096 x 11008], type = f16, quantizing .. size = 86.00 MB -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \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 -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[77/291] layers.8.attention.wk.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.052 0.078 0.104 0.125 0.134 0.125 0.104 0.078 0.052 0.033 0.019 0.022 \n",
"[78/291] layers.8.attention.wv.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.052 0.077 0.104 0.125 0.134 0.126 0.104 0.077 0.052 0.033 0.019 0.022 \n",
"[79/291] layers.8.attention.wo.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.132 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \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 -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[82/291] layers.8.feed_forward.w2.weight - [11008 x 4096], type = f16, quantizing .. size = 86.00 MB -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.052 0.077 0.104 0.126 0.134 0.126 0.104 0.078 0.052 0.033 0.019 0.022 \n",
"[83/291] layers.8.feed_forward.w3.weight - [4096 x 11008], type = f16, quantizing .. size = 86.00 MB -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \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 -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[86/291] layers.9.attention.wk.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.134 0.125 0.104 0.077 0.053 0.033 0.019 0.022 \n",
"[87/291] layers.9.attention.wv.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.052 0.077 0.104 0.126 0.134 0.125 0.104 0.077 0.052 0.033 0.019 0.022 \n",
"[88/291] layers.9.attention.wo.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.124 0.104 0.078 0.053 0.033 0.019 0.022 \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 -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[91/291] layers.9.feed_forward.w2.weight - [11008 x 4096], type = f16, quantizing .. size = 86.00 MB -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.052 0.077 0.104 0.126 0.134 0.126 0.104 0.077 0.052 0.033 0.019 0.022 \n",
"[92/291] layers.9.feed_forward.w3.weight - [4096 x 11008], type = f16, quantizing .. size = 86.00 MB -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \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 -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[95/291] layers.10.attention.wk.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.077 0.053 0.033 0.019 0.022 \n",
"[96/291] layers.10.attention.wv.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.052 0.077 0.104 0.126 0.135 0.126 0.104 0.077 0.052 0.033 0.019 0.022 \n",
"[97/291] layers.10.attention.wo.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.132 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \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 -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[100/291] layers.10.feed_forward.w2.weight - [11008 x 4096], type = f16, quantizing .. size = 86.00 MB -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.052 0.077 0.104 0.126 0.134 0.126 0.104 0.077 0.052 0.033 0.019 0.022 \n",
"[101/291] layers.10.feed_forward.w3.weight - [4096 x 11008], type = f16, quantizing .. size = 86.00 MB -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \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 -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[104/291] layers.11.attention.wk.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.134 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[105/291] layers.11.attention.wv.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.052 0.077 0.104 0.125 0.135 0.126 0.104 0.077 0.052 0.033 0.019 0.022 \n",
"[106/291] layers.11.attention.wo.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.132 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \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 -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[109/291] layers.11.feed_forward.w2.weight - [11008 x 4096], type = f16, quantizing .. size = 86.00 MB -> 26.88 MB | hist: 0.000 0.022 0.019 0.032 0.052 0.077 0.104 0.126 0.134 0.126 0.104 0.077 0.052 0.032 0.019 0.022 \n",
"[110/291] layers.11.feed_forward.w3.weight - [4096 x 11008], type = f16, quantizing .. size = 86.00 MB -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \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 -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[113/291] layers.12.attention.wk.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[114/291] layers.12.attention.wv.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.052 0.077 0.104 0.126 0.135 0.126 0.104 0.077 0.052 0.033 0.019 0.022 \n",
"[115/291] layers.12.attention.wo.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.132 0.124 0.104 0.078 0.053 0.033 0.019 0.022 \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 -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[118/291] layers.12.feed_forward.w2.weight - [11008 x 4096], type = f16, quantizing .. size = 86.00 MB -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.052 0.077 0.104 0.126 0.134 0.126 0.104 0.077 0.052 0.033 0.019 0.022 \n",
"[119/291] layers.12.feed_forward.w3.weight - [4096 x 11008], type = f16, quantizing .. size = 86.00 MB -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \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 -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[122/291] layers.13.attention.wk.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.134 0.125 0.104 0.078 0.052 0.033 0.019 0.022 \n",
"[123/291] layers.13.attention.wv.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.052 0.077 0.104 0.126 0.135 0.126 0.104 0.077 0.052 0.033 0.019 0.022 \n",
"[124/291] layers.13.attention.wo.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.124 0.132 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \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 -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[127/291] layers.13.feed_forward.w2.weight - [11008 x 4096], type = f16, quantizing .. size = 86.00 MB -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.052 0.077 0.104 0.126 0.134 0.126 0.104 0.078 0.052 0.033 0.019 0.022 \n",
"[128/291] layers.13.feed_forward.w3.weight - [4096 x 11008], type = f16, quantizing .. size = 86.00 MB -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \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 -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[131/291] layers.14.attention.wk.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[132/291] layers.14.attention.wv.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.052 0.077 0.104 0.125 0.134 0.125 0.104 0.077 0.052 0.033 0.019 0.022 \n",
"[133/291] layers.14.attention.wo.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.124 0.104 0.078 0.053 0.033 0.019 0.022 \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 -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[136/291] layers.14.feed_forward.w2.weight - [11008 x 4096], type = f16, quantizing .. size = 86.00 MB -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.052 0.077 0.104 0.126 0.134 0.126 0.104 0.077 0.052 0.033 0.019 0.022 \n",
"[137/291] layers.14.feed_forward.w3.weight - [4096 x 11008], type = f16, quantizing .. size = 86.00 MB -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \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 -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[140/291] layers.15.attention.wk.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[141/291] layers.15.attention.wv.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.052 0.077 0.104 0.126 0.134 0.126 0.104 0.077 0.053 0.033 0.019 0.022 \n",
"[142/291] layers.15.attention.wo.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.132 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \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 -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.132 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[145/291] layers.15.feed_forward.w2.weight - [11008 x 4096], type = f16, quantizing .. size = 86.00 MB -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.052 0.078 0.104 0.126 0.134 0.125 0.104 0.077 0.052 0.033 0.019 0.022 \n",
"[146/291] layers.15.feed_forward.w3.weight - [4096 x 11008], type = f16, quantizing .. size = 86.00 MB -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \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 -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[149/291] layers.16.attention.wk.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.134 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[150/291] layers.16.attention.wv.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.052 0.077 0.104 0.125 0.135 0.125 0.104 0.077 0.052 0.033 0.019 0.022 \n",
"[151/291] layers.16.attention.wo.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.132 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \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 -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.132 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[154/291] layers.16.feed_forward.w2.weight - [11008 x 4096], type = f16, quantizing .. size = 86.00 MB -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.052 0.078 0.104 0.126 0.134 0.126 0.104 0.078 0.052 0.033 0.019 0.022 \n",
"[155/291] layers.16.feed_forward.w3.weight - [4096 x 11008], type = f16, quantizing .. size = 86.00 MB -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \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 -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[158/291] layers.17.attention.wk.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.134 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[159/291] layers.17.attention.wv.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.052 0.077 0.104 0.126 0.134 0.125 0.104 0.077 0.052 0.033 0.019 0.022 \n",
"[160/291] layers.17.attention.wo.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.132 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \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 -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.132 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[163/291] layers.17.feed_forward.w2.weight - [11008 x 4096], type = f16, quantizing .. size = 86.00 MB -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.134 0.125 0.104 0.078 0.052 0.033 0.019 0.022 \n",
"[164/291] layers.17.feed_forward.w3.weight - [4096 x 11008], type = f16, quantizing .. size = 86.00 MB -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \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 -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[167/291] layers.18.attention.wk.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[168/291] layers.18.attention.wv.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.077 0.104 0.125 0.134 0.125 0.104 0.077 0.053 0.033 0.019 0.022 \n",
"[169/291] layers.18.attention.wo.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.124 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \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 -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.132 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[172/291] layers.18.feed_forward.w2.weight - [11008 x 4096], type = f16, quantizing .. size = 86.00 MB -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[173/291] layers.18.feed_forward.w3.weight - [4096 x 11008], type = f16, quantizing .. size = 86.00 MB -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \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 -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[176/291] layers.19.attention.wk.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.134 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[177/291] layers.19.attention.wv.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.052 0.078 0.104 0.125 0.134 0.125 0.104 0.077 0.053 0.033 0.019 0.022 \n",
"[178/291] layers.19.attention.wo.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.124 0.132 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \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 -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.132 0.124 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[181/291] layers.19.feed_forward.w2.weight - [11008 x 4096], type = f16, quantizing .. size = 86.00 MB -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[182/291] layers.19.feed_forward.w3.weight - [4096 x 11008], type = f16, quantizing .. size = 86.00 MB -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \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 -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[185/291] layers.20.attention.wk.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.134 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[186/291] layers.20.attention.wv.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.134 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[187/291] layers.20.attention.wo.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.132 0.124 0.104 0.078 0.053 0.033 0.019 0.022 \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 -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.132 0.124 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[190/291] layers.20.feed_forward.w2.weight - [11008 x 4096], type = f16, quantizing .. size = 86.00 MB -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[191/291] layers.20.feed_forward.w3.weight - [4096 x 11008], type = f16, quantizing .. size = 86.00 MB -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \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 -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[194/291] layers.21.attention.wk.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.077 0.104 0.125 0.134 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[195/291] layers.21.attention.wv.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.077 0.104 0.125 0.134 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[196/291] layers.21.attention.wo.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.124 0.132 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \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 -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.132 0.124 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[199/291] layers.21.feed_forward.w2.weight - [11008 x 4096], type = f16, quantizing .. size = 86.00 MB -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[200/291] layers.21.feed_forward.w3.weight - [4096 x 11008], type = f16, quantizing .. size = 86.00 MB -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \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 -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[203/291] layers.22.attention.wk.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.134 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[204/291] layers.22.attention.wv.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.134 0.125 0.104 0.077 0.053 0.033 0.019 0.022 \n",
"[205/291] layers.22.attention.wo.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.124 0.132 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \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 -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.132 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[208/291] layers.22.feed_forward.w2.weight - [11008 x 4096], type = f16, quantizing .. size = 86.00 MB -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[209/291] layers.22.feed_forward.w3.weight - [4096 x 11008], type = f16, quantizing .. size = 86.00 MB -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \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 -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[212/291] layers.23.attention.wk.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.077 0.104 0.125 0.134 0.125 0.104 0.077 0.053 0.033 0.019 0.022 \n",
"[213/291] layers.23.attention.wv.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.134 0.125 0.104 0.077 0.053 0.033 0.019 0.022 \n",
"[214/291] layers.23.attention.wo.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \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 -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.132 0.124 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[217/291] layers.23.feed_forward.w2.weight - [11008 x 4096], type = f16, quantizing .. size = 86.00 MB -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[218/291] layers.23.feed_forward.w3.weight - [4096 x 11008], type = f16, quantizing .. size = 86.00 MB -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \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 -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[221/291] layers.24.attention.wk.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.134 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[222/291] layers.24.attention.wv.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.134 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[223/291] layers.24.attention.wo.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.132 0.124 0.104 0.078 0.053 0.033 0.019 0.022 \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 -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.132 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[226/291] layers.24.feed_forward.w2.weight - [11008 x 4096], type = f16, quantizing .. size = 86.00 MB -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[227/291] layers.24.feed_forward.w3.weight - [4096 x 11008], type = f16, quantizing .. size = 86.00 MB -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \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 -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[230/291] layers.25.attention.wk.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[231/291] layers.25.attention.wv.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.134 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[232/291] layers.25.attention.wo.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \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 -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.132 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[235/291] layers.25.feed_forward.w2.weight - [11008 x 4096], type = f16, quantizing .. size = 86.00 MB -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[236/291] layers.25.feed_forward.w3.weight - [4096 x 11008], type = f16, quantizing .. size = 86.00 MB -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \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 -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[239/291] layers.26.attention.wk.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[240/291] layers.26.attention.wv.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.134 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[241/291] layers.26.attention.wo.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.132 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \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 -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.132 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[244/291] layers.26.feed_forward.w2.weight - [11008 x 4096], type = f16, quantizing .. size = 86.00 MB -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[245/291] layers.26.feed_forward.w3.weight - [4096 x 11008], type = f16, quantizing .. size = 86.00 MB -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \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 -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.134 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[248/291] layers.27.attention.wk.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.134 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[249/291] layers.27.attention.wv.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[250/291] layers.27.attention.wo.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \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 -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.132 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[253/291] layers.27.feed_forward.w2.weight - [11008 x 4096], type = f16, quantizing .. size = 86.00 MB -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[254/291] layers.27.feed_forward.w3.weight - [4096 x 11008], type = f16, quantizing .. size = 86.00 MB -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \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 -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.134 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[257/291] layers.28.attention.wk.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.052 0.078 0.104 0.125 0.134 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[258/291] layers.28.attention.wv.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.077 0.104 0.125 0.134 0.125 0.104 0.077 0.053 0.033 0.019 0.022 \n",
"[259/291] layers.28.attention.wo.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \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 -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.132 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[262/291] layers.28.feed_forward.w2.weight - [11008 x 4096], type = f16, quantizing .. size = 86.00 MB -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.052 0.078 0.104 0.125 0.134 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[263/291] layers.28.feed_forward.w3.weight - [4096 x 11008], type = f16, quantizing .. size = 86.00 MB -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \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 -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.134 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[266/291] layers.29.attention.wk.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.077 0.104 0.125 0.134 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[267/291] layers.29.attention.wv.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.134 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[268/291] layers.29.attention.wo.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \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 -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[271/291] layers.29.feed_forward.w2.weight - [11008 x 4096], type = f16, quantizing .. size = 86.00 MB -> 26.88 MB | hist: 0.000 0.022 0.019 0.032 0.052 0.077 0.104 0.126 0.134 0.126 0.104 0.077 0.052 0.032 0.019 0.022 \n",
"[272/291] layers.29.feed_forward.w3.weight - [4096 x 11008], type = f16, quantizing .. size = 86.00 MB -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \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 -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.077 0.104 0.126 0.134 0.125 0.104 0.077 0.052 0.033 0.019 0.022 \n",
"[275/291] layers.30.attention.wk.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.077 0.104 0.125 0.134 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[276/291] layers.30.attention.wv.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.077 0.104 0.125 0.134 0.125 0.104 0.077 0.053 0.033 0.019 0.022 \n",
"[277/291] layers.30.attention.wo.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \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 -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[280/291] layers.30.feed_forward.w2.weight - [11008 x 4096], type = f16, quantizing .. size = 86.00 MB -> 26.88 MB | hist: 0.000 0.022 0.018 0.032 0.051 0.076 0.104 0.128 0.137 0.128 0.104 0.076 0.051 0.032 0.018 0.022 \n",
"[281/291] layers.30.feed_forward.w3.weight - [4096 x 11008], type = f16, quantizing .. size = 86.00 MB -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \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 -> 10.00 MB | hist: 0.000 0.022 0.019 0.032 0.052 0.077 0.104 0.126 0.135 0.126 0.104 0.077 0.052 0.032 0.019 0.022 \n",
"[284/291] layers.31.attention.wk.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.052 0.077 0.104 0.126 0.134 0.126 0.104 0.077 0.052 0.033 0.019 0.022 \n",
"[285/291] layers.31.attention.wv.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.032 0.052 0.077 0.104 0.126 0.135 0.126 0.104 0.077 0.052 0.032 0.019 0.022 \n",
"[286/291] layers.31.attention.wo.weight - [4096 x 4096], type = f16, quantizing .. size = 32.00 MB -> 10.00 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \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 -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.133 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"[289/291] layers.31.feed_forward.w2.weight - [11008 x 4096], type = f16, quantizing .. size = 86.00 MB -> 26.88 MB | hist: 0.000 0.021 0.018 0.031 0.050 0.075 0.104 0.130 0.140 0.130 0.104 0.075 0.050 0.031 0.018 0.021 \n",
"[290/291] layers.31.feed_forward.w3.weight - [4096 x 11008], type = f16, quantizing .. size = 86.00 MB -> 26.88 MB | hist: 0.000 0.022 0.019 0.033 0.053 0.077 0.104 0.125 0.134 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \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 = 4104.93 MB\n",
"llama_model_quantize_internal: hist: 0.000 0.022 0.019 0.033 0.053 0.078 0.104 0.125 0.134 0.125 0.104 0.078 0.053 0.033 0.019 0.022 \n",
"\n",
"main: quantize time = 178732.41 ms\n",
"main: total time = 178732.41 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_0.bin --color -f ./prompts/alpaca.txt -p \"详细介绍一下北京的名胜古迹:\" -n 512"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "tW-ep1BsVQtG",
"outputId": "0706c974-127e-4f21-be6b-d71ea4fb989b"
},
"execution_count": 10,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"main: seed = 1681467955\n",
"llama.cpp: loading model from ./zh-models/7B/ggml-model-q4_0.bin\n",
"llama_model_load_internal: format = ggjt v1 (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 = 2 (mostly Q4_0)\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 = 59.11 KB\n",
"llama_model_load_internal: mem required = 5896.99 MB (+ 1026.00 MB per state)\n",
"llama_init_from_file: kv self size = 256.00 MB\n",
"\n",
"system_info: n_threads = 40 / 40 | AVX = 1 | AVX2 = 1 | AVX512 = 0 | FMA = 1 | NEON = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 0 | SSE3 = 1 | VSX = 0 | \n",
"sampling: temp = 0.800000, top_k = 40, top_p = 0.950000, repeat_last_n = 64, repeat_penalty = 1.100000\n",
"generate: n_ctx = 512, n_batch = 8, n_predict = 512, n_keep = 0\n",
"\n",
"\n",
"\u001b[33m 详细介绍一下北京的名胜古迹:\u001b[0m\n",
" 故宫:明、清两代皇室,御花园及八达门大街。 宫殿内有大量文物珍品; [end of text]\n",
"\n",
"llama_print_timings: load time = 717.01 ms\n",
"llama_print_timings: sample time = 48.97 ms / 32 runs ( 1.53 ms per run)\n",
"llama_print_timings: prompt eval time = 680.93 ms / 11 tokens ( 61.90 ms per token)\n",
"llama_print_timings: eval time = 4490.00 ms / 31 runs ( 144.84 ms per run)\n",
"llama_print_timings: total time = 5461.05 ms\n"
]
}
]
}
]
}