{ "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 [00:00 121.96 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" ] } ] } ] }