File size: 13,651 Bytes
9b1d4f8 ca8558a 9b1d4f8 ca8558a 9b1d4f8 ca8558a 9b1d4f8 ca8558a 9b1d4f8 ca8558a 9b1d4f8 ca8558a 9b1d4f8 ca8558a 9b1d4f8 ca8558a 9b1d4f8 ca8558a 9b1d4f8 ca8558a 9b1d4f8 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "3cb8b683-840f-4981-af83-018f067c5c94",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Defaulting to user installation because normal site-packages is not writeable\n",
"Collecting transformers\n",
" Downloading transformers-4.47.0-py3-none-any.whl (10.1 MB)\n",
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m10.1/10.1 MB\u001b[0m \u001b[31m59.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m00:01\u001b[0m0:01\u001b[0m\n",
"\u001b[?25hCollecting huggingface-hub<1.0,>=0.24.0\n",
" Downloading huggingface_hub-0.27.0-py3-none-any.whl (450 kB)\n",
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m450.5/450.5 KB\u001b[0m \u001b[31m36.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting tqdm>=4.27\n",
" Downloading tqdm-4.67.1-py3-none-any.whl (78 kB)\n",
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m78.5/78.5 KB\u001b[0m \u001b[31m12.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: numpy>=1.17 in /usr/lib/python3/dist-packages (from transformers) (1.21.5)\n",
"Requirement already satisfied: filelock in /usr/lib/python3/dist-packages (from transformers) (3.6.0)\n",
"Requirement already satisfied: packaging>=20.0 in /usr/lib/python3/dist-packages (from transformers) (21.3)\n",
"Collecting safetensors>=0.4.1\n",
" Downloading safetensors-0.4.5-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (435 kB)\n",
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m435.0/435.0 KB\u001b[0m \u001b[31m49.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting tokenizers<0.22,>=0.21\n",
" Downloading tokenizers-0.21.0-cp39-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (3.0 MB)\n",
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m3.0/3.0 MB\u001b[0m \u001b[31m71.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m:00:01\u001b[0m\n",
"\u001b[?25hCollecting regex!=2019.12.17\n",
" Downloading regex-2024.11.6-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (781 kB)\n",
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m781.7/781.7 KB\u001b[0m \u001b[31m59.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: requests in /usr/lib/python3/dist-packages (from transformers) (2.25.1)\n",
"Requirement already satisfied: pyyaml>=5.1 in /usr/lib/python3/dist-packages (from transformers) (5.4.1)\n",
"Requirement already satisfied: fsspec>=2023.5.0 in /usr/lib/python3/dist-packages (from huggingface-hub<1.0,>=0.24.0->transformers) (2024.3.1)\n",
"Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/lib/python3/dist-packages (from huggingface-hub<1.0,>=0.24.0->transformers) (4.9.0)\n",
"Installing collected packages: tqdm, safetensors, regex, huggingface-hub, tokenizers, transformers\n",
"Successfully installed huggingface-hub-0.27.0 regex-2024.11.6 safetensors-0.4.5 tokenizers-0.21.0 tqdm-4.67.1 transformers-4.47.0\n"
]
}
],
"source": [
"!pip install transformers"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "e3672a9c-c8ab-4d13-9498-5450ca3d95c3",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"README.md\t\t\t model-00002-of-00004.safetensors\n",
"Untitled.ipynb\t\t\t model-00003-of-00004.safetensors\n",
"Untitled1.ipynb\t\t\t model-00004-of-00004.safetensors\n",
"added_tokens.json\t\t model.safetensors.index.json\n",
"checkpoint-120\t\t\t pytorch_model-00001-of-00002.bin\n",
"checkpoint-40\t\t\t pytorch_model-00002-of-00002.bin\n",
"checkpoint-80\t\t\t pytorch_model.bin.index.json\n",
"checkpoint-90\t\t\t special_tokens_map.json\n",
"config.json\t\t\t tokenizer.json\n",
"generation_config.json\t\t tokenizer_config.json\n",
"merges.txt\t\t\t training_args.bin\n",
"model-00001-of-00004.safetensors vocab.json\n"
]
}
],
"source": [
"!ls"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "4a7a57e8-6bc3-4d15-88ac-942e8347b7cd",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Loading checkpoint shards: 100%|ββββββββββ| 4/4 [00:20<00:00, 5.04s/it]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Model and tokenizer loaded successfully!\n"
]
}
],
"source": [
"from transformers import AutoModelForCausalLM, AutoTokenizer\n",
"\n",
"# Path to your local checkpoint directory\n",
"checkpoint_path = \"checkpoint-162\"\n",
"\n",
"# Load the model and tokenizer\n",
"model = AutoModelForCausalLM.from_pretrained(checkpoint_path)\n",
"tokenizer = AutoTokenizer.from_pretrained(checkpoint_path)\n",
"\n",
"# Verify loading\n",
"print(\"Model and tokenizer loaded successfully!\")\n"
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "c3b9fcde-a4f3-4217-ba9a-cf799800cd63",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"RepoUrl('https://huggingface.co/neginashz/checkpoint-162', endpoint='https://huggingface.co', repo_type='model', repo_id='neginashz/checkpoint-162')"
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from huggingface_hub import create_repo\n",
"\n",
"create_repo(repo_id=\"neginashz/checkpoint-162\", private=False, exist_ok=True)\n"
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "6e19721a-b69c-42e6-a740-04e4b8ded4fa",
"metadata": {},
"outputs": [
{
"ename": "KeyboardInterrupt",
"evalue": "",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)",
"\u001b[0;32m/tmp/ipykernel_9719/2177510705.py\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mmodel\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpush_to_hub\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"neginashz/checkpoint-162\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 2\u001b[0m \u001b[0mtokenizer\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpush_to_hub\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"neginashz/checkpoint-162\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m~/.local/lib/python3.10/site-packages/transformers/modeling_utils.py\u001b[0m in \u001b[0;36mpush_to_hub\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 3085\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mtags\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 3086\u001b[0m \u001b[0mkwargs\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m\"tags\"\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtags\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 3087\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0msuper\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpush_to_hub\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 3088\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 3089\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0mget_memory_footprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mreturn_buffers\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mTrue\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m~/.local/lib/python3.10/site-packages/transformers/utils/hub.py\u001b[0m in \u001b[0;36mpush_to_hub\u001b[0;34m(self, repo_id, use_temp_dir, commit_message, private, token, max_shard_size, create_pr, safe_serialization, revision, commit_description, tags, **deprecated_kwargs)\u001b[0m\n\u001b[1;32m 947\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 948\u001b[0m \u001b[0;31m# Save all files.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 949\u001b[0;31m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msave_pretrained\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mwork_dir\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmax_shard_size\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mmax_shard_size\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0msafe_serialization\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0msafe_serialization\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 950\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 951\u001b[0m \u001b[0;31m# Update model card if needed:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m~/.local/lib/python3.10/site-packages/transformers/modeling_utils.py\u001b[0m in \u001b[0;36msave_pretrained\u001b[0;34m(self, save_directory, is_main_process, state_dict, save_function, push_to_hub, max_shard_size, safe_serialization, variant, token, save_peft_format, **kwargs)\u001b[0m\n\u001b[1;32m 3032\u001b[0m \u001b[0;31m# At some point we will need to deal better with save_function (used for TPU and other distributed\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 3033\u001b[0m \u001b[0;31m# joyfulness), but for now this enough.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 3034\u001b[0;31m \u001b[0msafe_save_file\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mshard\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mos\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpath\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mjoin\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0msave_directory\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mshard_file\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmetadata\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m{\u001b[0m\u001b[0;34m\"format\"\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;34m\"pt\"\u001b[0m\u001b[0;34m}\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 3035\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 3036\u001b[0m \u001b[0msave_function\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mshard\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mos\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpath\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mjoin\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0msave_directory\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mshard_file\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m~/.local/lib/python3.10/site-packages/safetensors/torch.py\u001b[0m in \u001b[0;36msave_file\u001b[0;34m(tensors, filename, metadata)\u001b[0m\n\u001b[1;32m 284\u001b[0m \u001b[0;31m`\u001b[0m\u001b[0;31m`\u001b[0m\u001b[0;31m`\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 285\u001b[0m \"\"\"\n\u001b[0;32m--> 286\u001b[0;31m \u001b[0mserialize_file\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0m_flatten\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtensors\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfilename\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmetadata\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mmetadata\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 287\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 288\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;31mKeyboardInterrupt\u001b[0m: "
]
}
],
"source": [
"model.push_to_hub(\"neginashz/checkpoint-162\")\n",
"tokenizer.push_to_hub(\"neginashz/checkpoint-162\")\n"
]
}
],
"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": "3.10.12"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
|