Files
airllm/air_llm/tests/test_notebooks/test_mlx.ipynb
2023-12-25 16:28:47 -06:00

1444 lines
74 KiB
Plaintext

{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# example of airllm on mac os"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from sys import platform\n",
"\n",
"assert platform == \"darwin\", \"this example is supposed to be run on mac os\"\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# install airllm"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"collapsed": true,
"jupyter": {
"outputs_hidden": true
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Collecting airllm\n",
" Using cached airllm-2.7-py3-none-any.whl.metadata (13 kB)\n",
"Collecting tqdm (from airllm)\n",
" Using cached tqdm-4.66.1-py3-none-any.whl.metadata (57 kB)\n",
"Requirement already satisfied: torch in /usr/local/anaconda3/envs/native/lib/python3.11/site-packages (from airllm) (2.1.0)\n",
"Collecting transformers (from airllm)\n",
" Using cached transformers-4.36.2-py3-none-any.whl.metadata (126 kB)\n",
"Collecting accelerate (from airllm)\n",
" Downloading accelerate-0.25.0-py3-none-any.whl.metadata (18 kB)\n",
"Collecting safetensors (from airllm)\n",
" Downloading safetensors-0.4.1-cp311-cp311-macosx_11_0_arm64.whl.metadata (3.8 kB)\n",
"Collecting optimum (from airllm)\n",
" Downloading optimum-1.16.1-py3-none-any.whl.metadata (17 kB)\n",
"Collecting huggingface-hub (from airllm)\n",
" Using cached huggingface_hub-0.20.1-py3-none-any.whl.metadata (12 kB)\n",
"Collecting scipy (from airllm)\n",
" Downloading scipy-1.11.4-cp311-cp311-macosx_12_0_arm64.whl.metadata (165 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m165.4/165.4 kB\u001b[0m \u001b[31m3.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0ma \u001b[36m0:00:01\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: numpy>=1.17 in /usr/local/anaconda3/envs/native/lib/python3.11/site-packages (from accelerate->airllm) (1.26.2)\n",
"Requirement already satisfied: packaging>=20.0 in /usr/local/anaconda3/envs/native/lib/python3.11/site-packages (from accelerate->airllm) (23.2)\n",
"Requirement already satisfied: psutil in /usr/local/anaconda3/envs/native/lib/python3.11/site-packages (from accelerate->airllm) (5.9.0)\n",
"Requirement already satisfied: pyyaml in /usr/local/anaconda3/envs/native/lib/python3.11/site-packages (from accelerate->airllm) (6.0.1)\n",
"Requirement already satisfied: filelock in /usr/local/anaconda3/envs/native/lib/python3.11/site-packages (from torch->airllm) (3.13.1)\n",
"Requirement already satisfied: typing-extensions in /usr/local/anaconda3/envs/native/lib/python3.11/site-packages (from torch->airllm) (4.7.1)\n",
"Requirement already satisfied: sympy in /usr/local/anaconda3/envs/native/lib/python3.11/site-packages (from torch->airllm) (1.12)\n",
"Requirement already satisfied: networkx in /usr/local/anaconda3/envs/native/lib/python3.11/site-packages (from torch->airllm) (3.1)\n",
"Requirement already satisfied: jinja2 in /usr/local/anaconda3/envs/native/lib/python3.11/site-packages (from torch->airllm) (3.1.2)\n",
"Requirement already satisfied: fsspec in /usr/local/anaconda3/envs/native/lib/python3.11/site-packages (from torch->airllm) (2023.10.0)\n",
"Requirement already satisfied: requests in /usr/local/anaconda3/envs/native/lib/python3.11/site-packages (from huggingface-hub->airllm) (2.31.0)\n",
"Collecting coloredlogs (from optimum->airllm)\n",
" Downloading coloredlogs-15.0.1-py2.py3-none-any.whl (46 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m46.0/46.0 kB\u001b[0m \u001b[31m4.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting datasets (from optimum->airllm)\n",
" Downloading datasets-2.16.0-py3-none-any.whl.metadata (20 kB)\n",
"Collecting regex!=2019.12.17 (from transformers->airllm)\n",
" Downloading regex-2023.12.25-cp311-cp311-macosx_11_0_arm64.whl.metadata (40 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m40.9/40.9 kB\u001b[0m \u001b[31m3.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting tokenizers<0.19,>=0.14 (from transformers->airllm)\n",
" Downloading tokenizers-0.15.0-cp311-cp311-macosx_11_0_arm64.whl.metadata (6.7 kB)\n",
"Collecting sentencepiece!=0.1.92,>=0.1.91 (from transformers[sentencepiece]>=4.26.0->optimum->airllm)\n",
" Downloading sentencepiece-0.1.99-cp311-cp311-macosx_11_0_arm64.whl (1.2 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.2/1.2 MB\u001b[0m \u001b[31m9.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0mta \u001b[36m0:00:01\u001b[0m\n",
"\u001b[?25hCollecting protobuf (from transformers[sentencepiece]>=4.26.0->optimum->airllm)\n",
" Downloading protobuf-4.25.1-cp37-abi3-macosx_10_9_universal2.whl.metadata (541 bytes)\n",
"Collecting humanfriendly>=9.1 (from coloredlogs->optimum->airllm)\n",
" Downloading humanfriendly-10.0-py2.py3-none-any.whl (86 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m86.8/86.8 kB\u001b[0m \u001b[31m4.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting pyarrow>=8.0.0 (from datasets->optimum->airllm)\n",
" Downloading pyarrow-14.0.2-cp311-cp311-macosx_11_0_arm64.whl.metadata (3.0 kB)\n",
"Collecting pyarrow-hotfix (from datasets->optimum->airllm)\n",
" Downloading pyarrow_hotfix-0.6-py3-none-any.whl.metadata (3.6 kB)\n",
"Collecting dill<0.3.8,>=0.3.0 (from datasets->optimum->airllm)\n",
" Downloading dill-0.3.7-py3-none-any.whl.metadata (9.9 kB)\n",
"Collecting pandas (from datasets->optimum->airllm)\n",
" Downloading pandas-2.1.4-cp311-cp311-macosx_11_0_arm64.whl.metadata (18 kB)\n",
"Collecting xxhash (from datasets->optimum->airllm)\n",
" Downloading xxhash-3.4.1-cp311-cp311-macosx_11_0_arm64.whl.metadata (12 kB)\n",
"Collecting multiprocess (from datasets->optimum->airllm)\n",
" Downloading multiprocess-0.70.15-py311-none-any.whl.metadata (7.2 kB)\n",
"Collecting aiohttp (from datasets->optimum->airllm)\n",
" Downloading aiohttp-3.9.1-cp311-cp311-macosx_11_0_arm64.whl.metadata (7.4 kB)\n",
"Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/anaconda3/envs/native/lib/python3.11/site-packages (from requests->huggingface-hub->airllm) (3.3.2)\n",
"Requirement already satisfied: idna<4,>=2.5 in /usr/local/anaconda3/envs/native/lib/python3.11/site-packages (from requests->huggingface-hub->airllm) (3.6)\n",
"Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/anaconda3/envs/native/lib/python3.11/site-packages (from requests->huggingface-hub->airllm) (2.1.0)\n",
"Requirement already satisfied: certifi>=2017.4.17 in /usr/local/anaconda3/envs/native/lib/python3.11/site-packages (from requests->huggingface-hub->airllm) (2023.11.17)\n",
"Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/anaconda3/envs/native/lib/python3.11/site-packages (from jinja2->torch->airllm) (2.1.1)\n",
"Requirement already satisfied: mpmath>=0.19 in /usr/local/anaconda3/envs/native/lib/python3.11/site-packages (from sympy->torch->airllm) (1.3.0)\n",
"Requirement already satisfied: attrs>=17.3.0 in /usr/local/anaconda3/envs/native/lib/python3.11/site-packages (from aiohttp->datasets->optimum->airllm) (23.1.0)\n",
"Collecting multidict<7.0,>=4.5 (from aiohttp->datasets->optimum->airllm)\n",
" Downloading multidict-6.0.4-cp311-cp311-macosx_11_0_arm64.whl (29 kB)\n",
"Collecting yarl<2.0,>=1.0 (from aiohttp->datasets->optimum->airllm)\n",
" Downloading yarl-1.9.4-cp311-cp311-macosx_11_0_arm64.whl.metadata (31 kB)\n",
"Collecting frozenlist>=1.1.1 (from aiohttp->datasets->optimum->airllm)\n",
" Downloading frozenlist-1.4.1-cp311-cp311-macosx_11_0_arm64.whl.metadata (12 kB)\n",
"Collecting aiosignal>=1.1.2 (from aiohttp->datasets->optimum->airllm)\n",
" Downloading aiosignal-1.3.1-py3-none-any.whl (7.6 kB)\n",
"Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/anaconda3/envs/native/lib/python3.11/site-packages (from pandas->datasets->optimum->airllm) (2.8.2)\n",
"Requirement already satisfied: pytz>=2020.1 in /usr/local/anaconda3/envs/native/lib/python3.11/site-packages (from pandas->datasets->optimum->airllm) (2023.3.post1)\n",
"Collecting tzdata>=2022.1 (from pandas->datasets->optimum->airllm)\n",
" Using cached tzdata-2023.3-py2.py3-none-any.whl (341 kB)\n",
"Requirement already satisfied: six>=1.5 in /usr/local/anaconda3/envs/native/lib/python3.11/site-packages (from python-dateutil>=2.8.2->pandas->datasets->optimum->airllm) (1.16.0)\n",
"Using cached airllm-2.7-py3-none-any.whl (34 kB)\n",
"Downloading accelerate-0.25.0-py3-none-any.whl (265 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m265.7/265.7 kB\u001b[0m \u001b[31m8.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading safetensors-0.4.1-cp311-cp311-macosx_11_0_arm64.whl (426 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m426.3/426.3 kB\u001b[0m \u001b[31m9.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0mta \u001b[36m0:00:01\u001b[0m\n",
"\u001b[?25hUsing cached huggingface_hub-0.20.1-py3-none-any.whl (330 kB)\n",
"Using cached tqdm-4.66.1-py3-none-any.whl (78 kB)\n",
"Downloading optimum-1.16.1-py3-none-any.whl (403 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m403.3/403.3 kB\u001b[0m \u001b[31m8.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0mta \u001b[36m0:00:01\u001b[0m\n",
"\u001b[?25hUsing cached transformers-4.36.2-py3-none-any.whl (8.2 MB)\n",
"Downloading scipy-1.11.4-cp311-cp311-macosx_12_0_arm64.whl (29.7 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m29.7/29.7 MB\u001b[0m \u001b[31m13.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m00:01\u001b[0m00:01\u001b[0m\n",
"\u001b[?25hDownloading regex-2023.12.25-cp311-cp311-macosx_11_0_arm64.whl (291 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m291.0/291.0 kB\u001b[0m \u001b[31m8.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading tokenizers-0.15.0-cp311-cp311-macosx_11_0_arm64.whl (2.5 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.5/2.5 MB\u001b[0m \u001b[31m8.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0ma \u001b[36m0:00:01\u001b[0m\n",
"\u001b[?25hDownloading datasets-2.16.0-py3-none-any.whl (507 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m507.1/507.1 kB\u001b[0m \u001b[31m9.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0mta \u001b[36m0:00:01\u001b[0m\n",
"\u001b[?25hDownloading dill-0.3.7-py3-none-any.whl (115 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m115.3/115.3 kB\u001b[0m \u001b[31m8.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading aiohttp-3.9.1-cp311-cp311-macosx_11_0_arm64.whl (386 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m386.8/386.8 kB\u001b[0m \u001b[31m10.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading pyarrow-14.0.2-cp311-cp311-macosx_11_0_arm64.whl (24.0 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m24.0/24.0 MB\u001b[0m \u001b[31m8.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m:00:01\u001b[0m00:01\u001b[0m\n",
"\u001b[?25hDownloading multiprocess-0.70.15-py311-none-any.whl (135 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m135.4/135.4 kB\u001b[0m \u001b[31m5.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading pandas-2.1.4-cp311-cp311-macosx_11_0_arm64.whl (10.8 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m10.8/10.8 MB\u001b[0m \u001b[31m8.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m00:01\u001b[0m00:01\u001b[0m\n",
"\u001b[?25hDownloading protobuf-4.25.1-cp37-abi3-macosx_10_9_universal2.whl (394 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m394.2/394.2 kB\u001b[0m \u001b[31m4.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m00:01\u001b[0m00:01\u001b[0m\n",
"\u001b[?25hDownloading pyarrow_hotfix-0.6-py3-none-any.whl (7.9 kB)\n",
"Downloading xxhash-3.4.1-cp311-cp311-macosx_11_0_arm64.whl (30 kB)\n",
"Downloading frozenlist-1.4.1-cp311-cp311-macosx_11_0_arm64.whl (53 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m53.4/53.4 kB\u001b[0m \u001b[31m3.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading yarl-1.9.4-cp311-cp311-macosx_11_0_arm64.whl (81 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m81.2/81.2 kB\u001b[0m \u001b[31m8.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hInstalling collected packages: sentencepiece, xxhash, tzdata, tqdm, scipy, safetensors, regex, pyarrow-hotfix, pyarrow, protobuf, multidict, humanfriendly, frozenlist, dill, yarl, pandas, multiprocess, huggingface-hub, coloredlogs, aiosignal, tokenizers, aiohttp, accelerate, transformers, datasets, optimum, airllm\n",
"Successfully installed accelerate-0.25.0 aiohttp-3.9.1 aiosignal-1.3.1 airllm-2.7 coloredlogs-15.0.1 datasets-2.16.0 dill-0.3.7 frozenlist-1.4.1 huggingface-hub-0.20.1 humanfriendly-10.0 multidict-6.0.4 multiprocess-0.70.15 optimum-1.16.1 pandas-2.1.4 protobuf-4.25.1 pyarrow-14.0.2 pyarrow-hotfix-0.6 regex-2023.12.25 safetensors-0.4.1 scipy-1.11.4 sentencepiece-0.1.99 tokenizers-0.15.0 tqdm-4.66.1 transformers-4.36.2 tzdata-2023.3 xxhash-3.4.1 yarl-1.9.4\n"
]
}
],
"source": [
"!pip install -U airllm"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"# copy local code to test\n",
"#!cp -r /Users/l_y_o/Work/Anima/air_llm/airllm/* /usr/local/anaconda3/envs/native/lib/python3.11/site-packages/airllm/"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# test airllm mlx"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"from airllm import AutoModel"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "bc02b05b26854198b6bd124287f74bf7",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"Fetching 1 files: 0%| | 0/1 [00:00<?, ?it/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "945203eb3eb34d48aa80fbf9bff634dd",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"Fetching 18 files: 0%| | 0/18 [00:00<?, ?it/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "667380fd90e74fde8e17a69d7f97a012",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"tokenizer.json: 0%| | 0.00/3.56M [00:00<?, ?B/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "f193778a98354093993a4fea300c5f82",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"tokenizer_config.json: 0%| | 0.00/320 [00:00<?, ?B/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "91ed61f306cb4b84a10d32f92235800a",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"model-00003-of-00007.safetensors: 0%| | 0.00/9.75G [00:00<?, ?B/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "601451d9a6484f9795ef93ea1d07ccc7",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"tokenizer.model: 0%| | 0.00/1.03M [00:00<?, ?B/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" 0%| | 0/63 [00:00<?, ?it/s]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Loading shard 1/7\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" 2%|██▉ | 1/63 [00:01<02:00, 1.94s/it]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"saved as: /Users/l_y_o/.cache/huggingface/hub/models--01-ai--Yi-34B/snapshots/9292541b776cae9f25cf40e14764dcffc12c8999/splitted_model/model.embed_tokens.mlx\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" 3%|█████▊ | 2/63 [00:04<02:04, 2.04s/it]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"saved as: /Users/l_y_o/.cache/huggingface/hub/models--01-ai--Yi-34B/snapshots/9292541b776cae9f25cf40e14764dcffc12c8999/splitted_model/model.layers.0.mlx\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" 5%|████████▋ | 3/63 [00:06<02:05, 2.09s/it]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"saved as: /Users/l_y_o/.cache/huggingface/hub/models--01-ai--Yi-34B/snapshots/9292541b776cae9f25cf40e14764dcffc12c8999/splitted_model/model.layers.1.mlx\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" 6%|███████████▌ | 4/63 [00:08<02:01, 2.06s/it]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"saved as: /Users/l_y_o/.cache/huggingface/hub/models--01-ai--Yi-34B/snapshots/9292541b776cae9f25cf40e14764dcffc12c8999/splitted_model/model.layers.2.mlx\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" 8%|██████████████▌ | 5/63 [00:10<01:55, 2.00s/it]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"saved as: /Users/l_y_o/.cache/huggingface/hub/models--01-ai--Yi-34B/snapshots/9292541b776cae9f25cf40e14764dcffc12c8999/splitted_model/model.layers.3.mlx\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" 10%|█████████████████▍ | 6/63 [00:12<02:01, 2.13s/it]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"saved as: /Users/l_y_o/.cache/huggingface/hub/models--01-ai--Yi-34B/snapshots/9292541b776cae9f25cf40e14764dcffc12c8999/splitted_model/model.layers.4.mlx\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" 11%|████████████████████▎ | 7/63 [00:15<02:08, 2.30s/it]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"saved as: /Users/l_y_o/.cache/huggingface/hub/models--01-ai--Yi-34B/snapshots/9292541b776cae9f25cf40e14764dcffc12c8999/splitted_model/model.layers.5.mlx\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" 13%|███████████████████████▏ | 8/63 [00:17<02:10, 2.38s/it]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"saved as: /Users/l_y_o/.cache/huggingface/hub/models--01-ai--Yi-34B/snapshots/9292541b776cae9f25cf40e14764dcffc12c8999/splitted_model/model.layers.6.mlx\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" 14%|██████████████████████████▏ | 9/63 [00:20<02:12, 2.45s/it]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"saved as: /Users/l_y_o/.cache/huggingface/hub/models--01-ai--Yi-34B/snapshots/9292541b776cae9f25cf40e14764dcffc12c8999/splitted_model/model.layers.7.mlx\n",
"Loading shard 2/7\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" 16%|████████████████████████████▉ | 10/63 [00:22<02:05, 2.37s/it]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"saved as: /Users/l_y_o/.cache/huggingface/hub/models--01-ai--Yi-34B/snapshots/9292541b776cae9f25cf40e14764dcffc12c8999/splitted_model/model.layers.8.mlx\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" 17%|███████████████████████████████▊ | 11/63 [00:24<02:02, 2.35s/it]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"saved as: /Users/l_y_o/.cache/huggingface/hub/models--01-ai--Yi-34B/snapshots/9292541b776cae9f25cf40e14764dcffc12c8999/splitted_model/model.layers.9.mlx\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" 19%|██████████████████████████████████▋ | 12/63 [00:27<01:59, 2.35s/it]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"saved as: /Users/l_y_o/.cache/huggingface/hub/models--01-ai--Yi-34B/snapshots/9292541b776cae9f25cf40e14764dcffc12c8999/splitted_model/model.layers.10.mlx\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" 21%|█████████████████████████████████████▌ | 13/63 [00:29<01:55, 2.32s/it]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"saved as: /Users/l_y_o/.cache/huggingface/hub/models--01-ai--Yi-34B/snapshots/9292541b776cae9f25cf40e14764dcffc12c8999/splitted_model/model.layers.11.mlx\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" 22%|████████████████████████████████████████▍ | 14/63 [00:31<01:51, 2.28s/it]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"saved as: /Users/l_y_o/.cache/huggingface/hub/models--01-ai--Yi-34B/snapshots/9292541b776cae9f25cf40e14764dcffc12c8999/splitted_model/model.layers.12.mlx\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" 24%|███████████████████████████████████████████▎ | 15/63 [00:34<01:53, 2.37s/it]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"saved as: /Users/l_y_o/.cache/huggingface/hub/models--01-ai--Yi-34B/snapshots/9292541b776cae9f25cf40e14764dcffc12c8999/splitted_model/model.layers.13.mlx\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" 25%|██████████████████████████████████████████████▏ | 16/63 [00:36<01:52, 2.40s/it]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"saved as: /Users/l_y_o/.cache/huggingface/hub/models--01-ai--Yi-34B/snapshots/9292541b776cae9f25cf40e14764dcffc12c8999/splitted_model/model.layers.14.mlx\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" 27%|█████████████████████████████████████████████████ | 17/63 [00:39<01:50, 2.41s/it]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"saved as: /Users/l_y_o/.cache/huggingface/hub/models--01-ai--Yi-34B/snapshots/9292541b776cae9f25cf40e14764dcffc12c8999/splitted_model/model.layers.15.mlx\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" 29%|████████████████████████████████████████████████████ | 18/63 [00:41<01:51, 2.47s/it]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"saved as: /Users/l_y_o/.cache/huggingface/hub/models--01-ai--Yi-34B/snapshots/9292541b776cae9f25cf40e14764dcffc12c8999/splitted_model/model.layers.16.mlx\n",
"Loading shard 3/7\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" 30%|██████████████████████████████████████████████████████▉ | 19/63 [00:43<01:46, 2.42s/it]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"saved as: /Users/l_y_o/.cache/huggingface/hub/models--01-ai--Yi-34B/snapshots/9292541b776cae9f25cf40e14764dcffc12c8999/splitted_model/model.layers.17.mlx\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" 32%|█████████████████████████████████████████████████████████▊ | 20/63 [00:46<01:41, 2.37s/it]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"saved as: /Users/l_y_o/.cache/huggingface/hub/models--01-ai--Yi-34B/snapshots/9292541b776cae9f25cf40e14764dcffc12c8999/splitted_model/model.layers.18.mlx\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" 33%|████████████████████████████████████████████████████████████▋ | 21/63 [00:48<01:35, 2.27s/it]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"saved as: /Users/l_y_o/.cache/huggingface/hub/models--01-ai--Yi-34B/snapshots/9292541b776cae9f25cf40e14764dcffc12c8999/splitted_model/model.layers.19.mlx\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" 35%|███████████████████████████████████████████████████████████████▌ | 22/63 [00:50<01:33, 2.29s/it]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"saved as: /Users/l_y_o/.cache/huggingface/hub/models--01-ai--Yi-34B/snapshots/9292541b776cae9f25cf40e14764dcffc12c8999/splitted_model/model.layers.20.mlx\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" 37%|██████████████████████████████████████████████████████████████████▍ | 23/63 [00:52<01:29, 2.25s/it]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"saved as: /Users/l_y_o/.cache/huggingface/hub/models--01-ai--Yi-34B/snapshots/9292541b776cae9f25cf40e14764dcffc12c8999/splitted_model/model.layers.21.mlx\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" 38%|█████████████████████████████████████████████████████████████████████▎ | 24/63 [00:54<01:25, 2.20s/it]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"saved as: /Users/l_y_o/.cache/huggingface/hub/models--01-ai--Yi-34B/snapshots/9292541b776cae9f25cf40e14764dcffc12c8999/splitted_model/model.layers.22.mlx\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" 40%|████████████████████████████████████████████████████████████████████████▏ | 25/63 [00:57<01:24, 2.21s/it]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"saved as: /Users/l_y_o/.cache/huggingface/hub/models--01-ai--Yi-34B/snapshots/9292541b776cae9f25cf40e14764dcffc12c8999/splitted_model/model.layers.23.mlx\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" 41%|███████████████████████████████████████████████████████████████████████████ | 26/63 [00:59<01:20, 2.18s/it]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"saved as: /Users/l_y_o/.cache/huggingface/hub/models--01-ai--Yi-34B/snapshots/9292541b776cae9f25cf40e14764dcffc12c8999/splitted_model/model.layers.24.mlx\n",
"Loading shard 4/7\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" 43%|██████████████████████████████████████████████████████████████████████████████ | 27/63 [01:01<01:22, 2.28s/it]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"saved as: /Users/l_y_o/.cache/huggingface/hub/models--01-ai--Yi-34B/snapshots/9292541b776cae9f25cf40e14764dcffc12c8999/splitted_model/model.layers.25.mlx\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" 44%|████████████████████████████████████████████████████████████████████████████████▉ | 28/63 [01:04<01:20, 2.29s/it]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"saved as: /Users/l_y_o/.cache/huggingface/hub/models--01-ai--Yi-34B/snapshots/9292541b776cae9f25cf40e14764dcffc12c8999/splitted_model/model.layers.26.mlx\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" 46%|███████████████████████████████████████████████████████████████████████████████████▊ | 29/63 [01:06<01:15, 2.23s/it]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"saved as: /Users/l_y_o/.cache/huggingface/hub/models--01-ai--Yi-34B/snapshots/9292541b776cae9f25cf40e14764dcffc12c8999/splitted_model/model.layers.27.mlx\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" 48%|██████████████████████████████████████████████████████████████████████████████████████▋ | 30/63 [01:08<01:14, 2.26s/it]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"saved as: /Users/l_y_o/.cache/huggingface/hub/models--01-ai--Yi-34B/snapshots/9292541b776cae9f25cf40e14764dcffc12c8999/splitted_model/model.layers.28.mlx\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" 49%|█████████████████████████████████████████████████████████████████████████████████████████▌ | 31/63 [01:10<01:11, 2.25s/it]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"saved as: /Users/l_y_o/.cache/huggingface/hub/models--01-ai--Yi-34B/snapshots/9292541b776cae9f25cf40e14764dcffc12c8999/splitted_model/model.layers.29.mlx\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" 51%|████████████████████████████████████████████████████████████████████████████████████████████▍ | 32/63 [01:12<01:08, 2.21s/it]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"saved as: /Users/l_y_o/.cache/huggingface/hub/models--01-ai--Yi-34B/snapshots/9292541b776cae9f25cf40e14764dcffc12c8999/splitted_model/model.layers.30.mlx\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" 52%|███████████████████████████████████████████████████████████████████████████████████████████████▎ | 33/63 [01:15<01:07, 2.24s/it]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"saved as: /Users/l_y_o/.cache/huggingface/hub/models--01-ai--Yi-34B/snapshots/9292541b776cae9f25cf40e14764dcffc12c8999/splitted_model/model.layers.31.mlx\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" 54%|██████████████████████████████████████████████████████████████████████████████████████████████████▏ | 34/63 [01:17<01:08, 2.37s/it]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"saved as: /Users/l_y_o/.cache/huggingface/hub/models--01-ai--Yi-34B/snapshots/9292541b776cae9f25cf40e14764dcffc12c8999/splitted_model/model.layers.32.mlx\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" 56%|█████████████████████████████████████████████████████████████████████████████████████████████████████ | 35/63 [01:20<01:09, 2.48s/it]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"saved as: /Users/l_y_o/.cache/huggingface/hub/models--01-ai--Yi-34B/snapshots/9292541b776cae9f25cf40e14764dcffc12c8999/splitted_model/model.layers.33.mlx\n",
"Loading shard 5/7\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" 57%|████████████████████████████████████████████████████████████████████████████████████████████████████████ | 36/63 [01:22<01:03, 2.35s/it]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"saved as: /Users/l_y_o/.cache/huggingface/hub/models--01-ai--Yi-34B/snapshots/9292541b776cae9f25cf40e14764dcffc12c8999/splitted_model/model.layers.34.mlx\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" 59%|██████████████████████████████████████████████████████████████████████████████████████████████████████████▉ | 37/63 [01:24<00:59, 2.28s/it]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"saved as: /Users/l_y_o/.cache/huggingface/hub/models--01-ai--Yi-34B/snapshots/9292541b776cae9f25cf40e14764dcffc12c8999/splitted_model/model.layers.35.mlx\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" 60%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████▊ | 38/63 [01:27<00:57, 2.31s/it]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"saved as: /Users/l_y_o/.cache/huggingface/hub/models--01-ai--Yi-34B/snapshots/9292541b776cae9f25cf40e14764dcffc12c8999/splitted_model/model.layers.36.mlx\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" 62%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████▋ | 39/63 [01:29<00:56, 2.35s/it]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"saved as: /Users/l_y_o/.cache/huggingface/hub/models--01-ai--Yi-34B/snapshots/9292541b776cae9f25cf40e14764dcffc12c8999/splitted_model/model.layers.37.mlx\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" 63%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████▌ | 40/63 [01:32<00:55, 2.42s/it]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"saved as: /Users/l_y_o/.cache/huggingface/hub/models--01-ai--Yi-34B/snapshots/9292541b776cae9f25cf40e14764dcffc12c8999/splitted_model/model.layers.38.mlx\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" 65%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▍ | 41/63 [01:34<00:53, 2.45s/it]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"saved as: /Users/l_y_o/.cache/huggingface/hub/models--01-ai--Yi-34B/snapshots/9292541b776cae9f25cf40e14764dcffc12c8999/splitted_model/model.layers.39.mlx\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" 67%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▎ | 42/63 [01:36<00:50, 2.38s/it]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"saved as: /Users/l_y_o/.cache/huggingface/hub/models--01-ai--Yi-34B/snapshots/9292541b776cae9f25cf40e14764dcffc12c8999/splitted_model/model.layers.40.mlx\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" 68%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▏ | 43/63 [01:39<00:48, 2.41s/it]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"saved as: /Users/l_y_o/.cache/huggingface/hub/models--01-ai--Yi-34B/snapshots/9292541b776cae9f25cf40e14764dcffc12c8999/splitted_model/model.layers.41.mlx\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" 70%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████ | 44/63 [01:41<00:46, 2.45s/it]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"saved as: /Users/l_y_o/.cache/huggingface/hub/models--01-ai--Yi-34B/snapshots/9292541b776cae9f25cf40e14764dcffc12c8999/splitted_model/model.layers.42.mlx\n",
"Loading shard 6/7\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" 71%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████ | 45/63 [01:44<00:44, 2.48s/it]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"saved as: /Users/l_y_o/.cache/huggingface/hub/models--01-ai--Yi-34B/snapshots/9292541b776cae9f25cf40e14764dcffc12c8999/splitted_model/model.layers.43.mlx\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" 73%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▉ | 46/63 [01:46<00:41, 2.46s/it]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"saved as: /Users/l_y_o/.cache/huggingface/hub/models--01-ai--Yi-34B/snapshots/9292541b776cae9f25cf40e14764dcffc12c8999/splitted_model/model.layers.44.mlx\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" 75%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▊ | 47/63 [01:49<00:39, 2.47s/it]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"saved as: /Users/l_y_o/.cache/huggingface/hub/models--01-ai--Yi-34B/snapshots/9292541b776cae9f25cf40e14764dcffc12c8999/splitted_model/model.layers.45.mlx\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" 76%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▋ | 48/63 [01:51<00:35, 2.37s/it]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"saved as: /Users/l_y_o/.cache/huggingface/hub/models--01-ai--Yi-34B/snapshots/9292541b776cae9f25cf40e14764dcffc12c8999/splitted_model/model.layers.46.mlx\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" 78%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▌ | 49/63 [01:53<00:32, 2.35s/it]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"saved as: /Users/l_y_o/.cache/huggingface/hub/models--01-ai--Yi-34B/snapshots/9292541b776cae9f25cf40e14764dcffc12c8999/splitted_model/model.layers.47.mlx\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" 79%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▍ | 50/63 [01:56<00:30, 2.38s/it]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"saved as: /Users/l_y_o/.cache/huggingface/hub/models--01-ai--Yi-34B/snapshots/9292541b776cae9f25cf40e14764dcffc12c8999/splitted_model/model.layers.48.mlx\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" 81%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▎ | 51/63 [01:58<00:29, 2.42s/it]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"saved as: /Users/l_y_o/.cache/huggingface/hub/models--01-ai--Yi-34B/snapshots/9292541b776cae9f25cf40e14764dcffc12c8999/splitted_model/model.layers.49.mlx\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" 83%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▏ | 52/63 [02:01<00:27, 2.51s/it]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"saved as: /Users/l_y_o/.cache/huggingface/hub/models--01-ai--Yi-34B/snapshots/9292541b776cae9f25cf40e14764dcffc12c8999/splitted_model/model.layers.50.mlx\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" 84%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████ | 53/63 [02:04<00:25, 2.56s/it]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"saved as: /Users/l_y_o/.cache/huggingface/hub/models--01-ai--Yi-34B/snapshots/9292541b776cae9f25cf40e14764dcffc12c8999/splitted_model/model.layers.51.mlx\n",
"Loading shard 7/7\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" 86%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████ | 54/63 [02:06<00:22, 2.50s/it]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"saved as: /Users/l_y_o/.cache/huggingface/hub/models--01-ai--Yi-34B/snapshots/9292541b776cae9f25cf40e14764dcffc12c8999/splitted_model/model.layers.52.mlx\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" 87%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▉ | 55/63 [02:08<00:19, 2.43s/it]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"saved as: /Users/l_y_o/.cache/huggingface/hub/models--01-ai--Yi-34B/snapshots/9292541b776cae9f25cf40e14764dcffc12c8999/splitted_model/model.layers.53.mlx\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" 89%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▊ | 56/63 [02:11<00:17, 2.44s/it]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"saved as: /Users/l_y_o/.cache/huggingface/hub/models--01-ai--Yi-34B/snapshots/9292541b776cae9f25cf40e14764dcffc12c8999/splitted_model/model.layers.54.mlx\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" 90%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▋ | 57/63 [02:13<00:15, 2.51s/it]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"saved as: /Users/l_y_o/.cache/huggingface/hub/models--01-ai--Yi-34B/snapshots/9292541b776cae9f25cf40e14764dcffc12c8999/splitted_model/model.layers.55.mlx\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" 92%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▌ | 58/63 [02:16<00:13, 2.61s/it]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"saved as: /Users/l_y_o/.cache/huggingface/hub/models--01-ai--Yi-34B/snapshots/9292541b776cae9f25cf40e14764dcffc12c8999/splitted_model/model.layers.56.mlx\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" 94%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▍ | 59/63 [02:19<00:10, 2.72s/it]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"saved as: /Users/l_y_o/.cache/huggingface/hub/models--01-ai--Yi-34B/snapshots/9292541b776cae9f25cf40e14764dcffc12c8999/splitted_model/model.layers.57.mlx\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" 95%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▎ | 60/63 [02:23<00:09, 3.17s/it]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"saved as: /Users/l_y_o/.cache/huggingface/hub/models--01-ai--Yi-34B/snapshots/9292541b776cae9f25cf40e14764dcffc12c8999/splitted_model/model.layers.58.mlx\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" 97%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▏ | 61/63 [02:41<00:15, 7.60s/it]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"saved as: /Users/l_y_o/.cache/huggingface/hub/models--01-ai--Yi-34B/snapshots/9292541b776cae9f25cf40e14764dcffc12c8999/splitted_model/model.layers.59.mlx\n",
"saved as: /Users/l_y_o/.cache/huggingface/hub/models--01-ai--Yi-34B/snapshots/9292541b776cae9f25cf40e14764dcffc12c8999/splitted_model/model.norm.mlx\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 63/63 [02:45<00:00, 2.62s/it]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"saved as: /Users/l_y_o/.cache/huggingface/hub/models--01-ai--Yi-34B/snapshots/9292541b776cae9f25cf40e14764dcffc12c8999/splitted_model/lm_head.mlx\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\n"
]
}
],
"source": [
"model = AutoModel.from_pretrained(\"01-ai/Yi-34B\")#\"garage-bAInd/Platypus2-7B\")"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'input_ids': array([[59597, 947]])}"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"input_text = [\n",
" #'What is the capital of United States?',\n",
" 'I like',\n",
" ]\n",
"\n",
"MAX_LENGTH = 128\n",
"input_tokens = model.tokenizer(input_text,\n",
" return_tensors=\"np\", \n",
" return_attention_mask=False, \n",
" truncation=True, \n",
" max_length=MAX_LENGTH, \n",
" padding=False)\n",
"\n",
"input_tokens"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 60/60 [00:53<00:00, 1.12it/s]\n",
"100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 60/60 [00:55<00:00, 1.09it/s]\n",
"100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 60/60 [00:53<00:00, 1.12it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
" to think that\n"
]
}
],
"source": [
"\n",
"import mlx.core as mx\n",
"generation_output = model.generate(\n",
" mx.array(input_tokens['input_ids']), \n",
" max_new_tokens=3,\n",
" use_cache=True,\n",
" return_dict_in_generate=True)\n",
"\n",
"print(generation_output)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# test Platypus2 7b"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"from airllm import AutoModel"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "9abc1702b4c34ed69aba9442d745cc29",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"Fetching 0 files: 0it [00:00, ?it/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "92138b9c855b41c4a91eb92dee9404bf",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"Fetching 12 files: 0%| | 0/12 [00:00<?, ?it/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"saved layers already found in /Users/l_y_o/.cache/huggingface/hub/models--garage-bAInd--Platypus2-7B/snapshots/c27aff7201e611f301c0e19f351cbe74b1a9f1f1/splitted_model\n"
]
}
],
"source": [
"model = AutoModel.from_pretrained(\"garage-bAInd/Platypus2-7B\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'input_ids': array([[ 1, 306, 763]])}"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"input_text = [\n",
" #'What is the capital of United States?',\n",
" 'I like',\n",
" ]\n",
"\n",
"MAX_LENGTH = 128\n",
"input_tokens = model.tokenizer(input_text,\n",
" return_tensors=\"np\", \n",
" return_attention_mask=False, \n",
" truncation=True, \n",
" max_length=MAX_LENGTH, \n",
" padding=False)\n",
"\n",
"input_tokens"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"running layers:: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:08<00:00, 3.95it/s]\n",
"running layers:: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:08<00:00, 3.66it/s]\n",
"running layers:: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [00:07<00:00, 4.06it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"to think of\n"
]
}
],
"source": [
"\n",
"import mlx.core as mx\n",
"generation_output = model.generate(\n",
" mx.array(input_tokens['input_ids']), \n",
" max_new_tokens=3,\n",
" use_cache=True,\n",
" return_dict_in_generate=True)\n",
"\n",
"print(generation_output)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.5"
}
},
"nbformat": 4,
"nbformat_minor": 4
}