Spaces:
No application file
No application file
Upload folder using huggingface_hub
Browse files- .ipynb_checkpoints/Untitled-checkpoint.ipynb +513 -0
- .ipynb_checkpoints/added_tokens-checkpoint.json +40 -0
- Untitled.ipynb +593 -0
- added_tokens.json +40 -0
- config.json +30 -0
- generation_config.json +4 -0
- merges.txt +0 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +348 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer_config.json +325 -0
- trainer_state.json +68 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.ipynb_checkpoints/Untitled-checkpoint.ipynb
ADDED
|
@@ -0,0 +1,513 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cells": [
|
| 3 |
+
{
|
| 4 |
+
"cell_type": "code",
|
| 5 |
+
"execution_count": 20,
|
| 6 |
+
"id": "88d5b164-4be8-4cce-b271-75c6de9e662a",
|
| 7 |
+
"metadata": {},
|
| 8 |
+
"outputs": [
|
| 9 |
+
{
|
| 10 |
+
"data": {
|
| 11 |
+
"text/plain": [
|
| 12 |
+
"PhiModel(\n",
|
| 13 |
+
" (embed_tokens): Embedding(51200, 2048)\n",
|
| 14 |
+
" (embed_dropout): Dropout(p=0.0, inplace=False)\n",
|
| 15 |
+
" (layers): ModuleList(\n",
|
| 16 |
+
" (0-23): 24 x PhiDecoderLayer(\n",
|
| 17 |
+
" (self_attn): PhiAttention(\n",
|
| 18 |
+
" (q_proj): Linear(in_features=2048, out_features=2048, bias=True)\n",
|
| 19 |
+
" (k_proj): Linear(in_features=2048, out_features=2048, bias=True)\n",
|
| 20 |
+
" (v_proj): Linear(in_features=2048, out_features=2048, bias=True)\n",
|
| 21 |
+
" (dense): Linear(in_features=2048, out_features=2048, bias=True)\n",
|
| 22 |
+
" (rotary_emb): PhiRotaryEmbedding()\n",
|
| 23 |
+
" )\n",
|
| 24 |
+
" (mlp): PhiMLP(\n",
|
| 25 |
+
" (activation_fn): NewGELUActivation()\n",
|
| 26 |
+
" (fc1): Linear(in_features=2048, out_features=8192, bias=True)\n",
|
| 27 |
+
" (fc2): Linear(in_features=8192, out_features=2048, bias=True)\n",
|
| 28 |
+
" )\n",
|
| 29 |
+
" (input_layernorm): LayerNorm((2048,), eps=1e-05, elementwise_affine=True)\n",
|
| 30 |
+
" (resid_dropout): Dropout(p=0.0, inplace=False)\n",
|
| 31 |
+
" )\n",
|
| 32 |
+
" )\n",
|
| 33 |
+
" (final_layernorm): LayerNorm((2048,), eps=1e-05, elementwise_affine=True)\n",
|
| 34 |
+
")"
|
| 35 |
+
]
|
| 36 |
+
},
|
| 37 |
+
"execution_count": 20,
|
| 38 |
+
"metadata": {},
|
| 39 |
+
"output_type": "execute_result"
|
| 40 |
+
}
|
| 41 |
+
],
|
| 42 |
+
"source": [
|
| 43 |
+
"from transformers import AutoModel, AutoTokenizer, AutoConfig\n",
|
| 44 |
+
"\n",
|
| 45 |
+
"# Specify the path to your checkpoint directory\n",
|
| 46 |
+
"checkpoint_dir = \"/workspace/OpenRLHF3/checkpoint/llama-3-8b-rlhf/iter_14\"\n",
|
| 47 |
+
"\n",
|
| 48 |
+
"# Load the model configuration\n",
|
| 49 |
+
"config = AutoConfig.from_pretrained(checkpoint_dir)\n",
|
| 50 |
+
"\n",
|
| 51 |
+
"# Load the tokenizer\n",
|
| 52 |
+
"tokenizer = AutoTokenizer.from_pretrained(checkpoint_dir)\n",
|
| 53 |
+
"\n",
|
| 54 |
+
"# Load the model using the safetensors files\n",
|
| 55 |
+
"model = AutoModel.from_pretrained(checkpoint_dir)\n",
|
| 56 |
+
"\n",
|
| 57 |
+
"# Set the model to evaluation mode\n",
|
| 58 |
+
"model.eval()\n",
|
| 59 |
+
"\n",
|
| 60 |
+
"# Now the model is ready to use for inference"
|
| 61 |
+
]
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"cell_type": "code",
|
| 65 |
+
"execution_count": 11,
|
| 66 |
+
"id": "3f4721b1-0853-47a0-88b4-7720a0ef79ee",
|
| 67 |
+
"metadata": {},
|
| 68 |
+
"outputs": [
|
| 69 |
+
{
|
| 70 |
+
"data": {
|
| 71 |
+
"application/vnd.jupyter.widget-view+json": {
|
| 72 |
+
"model_id": "3862f17dcf0d46998871e14b6324e47f",
|
| 73 |
+
"version_major": 2,
|
| 74 |
+
"version_minor": 0
|
| 75 |
+
},
|
| 76 |
+
"text/plain": [
|
| 77 |
+
"model-00001-of-00002.safetensors: 0%| | 0.00/4.98G [00:00<?, ?B/s]"
|
| 78 |
+
]
|
| 79 |
+
},
|
| 80 |
+
"metadata": {},
|
| 81 |
+
"output_type": "display_data"
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"data": {
|
| 85 |
+
"application/vnd.jupyter.widget-view+json": {
|
| 86 |
+
"model_id": "846214a9ecc446128aac3e409588581e",
|
| 87 |
+
"version_major": 2,
|
| 88 |
+
"version_minor": 0
|
| 89 |
+
},
|
| 90 |
+
"text/plain": [
|
| 91 |
+
"model-00002-of-00002.safetensors: 0%| | 0.00/269M [00:00<?, ?B/s]"
|
| 92 |
+
]
|
| 93 |
+
},
|
| 94 |
+
"metadata": {},
|
| 95 |
+
"output_type": "display_data"
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"data": {
|
| 99 |
+
"application/vnd.jupyter.widget-view+json": {
|
| 100 |
+
"model_id": "66f069e0e7bc4d5391170a352c323372",
|
| 101 |
+
"version_major": 2,
|
| 102 |
+
"version_minor": 0
|
| 103 |
+
},
|
| 104 |
+
"text/plain": [
|
| 105 |
+
"Upload 2 LFS files: 0%| | 0/2 [00:00<?, ?it/s]"
|
| 106 |
+
]
|
| 107 |
+
},
|
| 108 |
+
"metadata": {},
|
| 109 |
+
"output_type": "display_data"
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"data": {
|
| 113 |
+
"text/plain": [
|
| 114 |
+
"CommitInfo(commit_url='https://huggingface.co/OpenOpenAI/ppo_iter_14/commit/f131fe145e8337eb720d51d26379a261d7cc38df', commit_message='Upload model', commit_description='', oid='f131fe145e8337eb720d51d26379a261d7cc38df', pr_url=None, pr_revision=None, pr_num=None)"
|
| 115 |
+
]
|
| 116 |
+
},
|
| 117 |
+
"execution_count": 11,
|
| 118 |
+
"metadata": {},
|
| 119 |
+
"output_type": "execute_result"
|
| 120 |
+
}
|
| 121 |
+
],
|
| 122 |
+
"source": [
|
| 123 |
+
"model.push_to_hub('OpenOpenAI/ppo_iter_14')"
|
| 124 |
+
]
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"cell_type": "code",
|
| 128 |
+
"execution_count": 21,
|
| 129 |
+
"id": "6b467741-9810-4495-a968-64bdeb8d55cd",
|
| 130 |
+
"metadata": {},
|
| 131 |
+
"outputs": [
|
| 132 |
+
{
|
| 133 |
+
"data": {
|
| 134 |
+
"text/plain": [
|
| 135 |
+
"CommitInfo(commit_url='https://huggingface.co/OpenOpenAI/ppo_iter_14/commit/3f245ca9967e3784192045bd2064da5801d6e171', commit_message='Upload config', commit_description='', oid='3f245ca9967e3784192045bd2064da5801d6e171', pr_url=None, pr_revision=None, pr_num=None)"
|
| 136 |
+
]
|
| 137 |
+
},
|
| 138 |
+
"execution_count": 21,
|
| 139 |
+
"metadata": {},
|
| 140 |
+
"output_type": "execute_result"
|
| 141 |
+
}
|
| 142 |
+
],
|
| 143 |
+
"source": [
|
| 144 |
+
"config.push_to_hub('OpenOpenAI/ppo_iter_14')"
|
| 145 |
+
]
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"cell_type": "code",
|
| 149 |
+
"execution_count": 17,
|
| 150 |
+
"id": "37bb8dbb-f2cd-46cd-bdcd-906b0ae6e74e",
|
| 151 |
+
"metadata": {},
|
| 152 |
+
"outputs": [
|
| 153 |
+
{
|
| 154 |
+
"data": {
|
| 155 |
+
"application/vnd.jupyter.widget-view+json": {
|
| 156 |
+
"model_id": "c2857b5b6b824996a40de218bbab77f2",
|
| 157 |
+
"version_major": 2,
|
| 158 |
+
"version_minor": 0
|
| 159 |
+
},
|
| 160 |
+
"text/plain": [
|
| 161 |
+
"README.md: 0%| | 0.00/5.17k [00:00<?, ?B/s]"
|
| 162 |
+
]
|
| 163 |
+
},
|
| 164 |
+
"metadata": {},
|
| 165 |
+
"output_type": "display_data"
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"data": {
|
| 169 |
+
"text/plain": [
|
| 170 |
+
"CommitInfo(commit_url='https://huggingface.co/OpenOpenAI/checkpoint-2500/commit/77f7dc75043b34bc2e8b677cf9bc9440a4b56937', commit_message='Upload tokenizer', commit_description='', oid='77f7dc75043b34bc2e8b677cf9bc9440a4b56937', pr_url=None, pr_revision=None, pr_num=None)"
|
| 171 |
+
]
|
| 172 |
+
},
|
| 173 |
+
"execution_count": 17,
|
| 174 |
+
"metadata": {},
|
| 175 |
+
"output_type": "execute_result"
|
| 176 |
+
}
|
| 177 |
+
],
|
| 178 |
+
"source": [
|
| 179 |
+
"tokenizer.push_to_hub('OpenOpenAI/checkpoint-2500')"
|
| 180 |
+
]
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"cell_type": "code",
|
| 184 |
+
"execution_count": 19,
|
| 185 |
+
"id": "62eedc73-6524-4cdb-933a-702e1812b9bb",
|
| 186 |
+
"metadata": {},
|
| 187 |
+
"outputs": [
|
| 188 |
+
{
|
| 189 |
+
"data": {
|
| 190 |
+
"text/plain": [
|
| 191 |
+
"CommitInfo(commit_url='https://huggingface.co/OpenOpenAI/checkpoint-2500/commit/ccdb68475a6b305183c27d9772fd4af0949f78b5', commit_message='Upload config', commit_description='', oid='ccdb68475a6b305183c27d9772fd4af0949f78b5', pr_url=None, pr_revision=None, pr_num=None)"
|
| 192 |
+
]
|
| 193 |
+
},
|
| 194 |
+
"execution_count": 19,
|
| 195 |
+
"metadata": {},
|
| 196 |
+
"output_type": "execute_result"
|
| 197 |
+
}
|
| 198 |
+
],
|
| 199 |
+
"source": [
|
| 200 |
+
"config.push_to_hub('OpenOpenAI/checkpoint-2500')"
|
| 201 |
+
]
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"cell_type": "code",
|
| 205 |
+
"execution_count": 18,
|
| 206 |
+
"id": "acc6a23e-c7c7-404e-a51f-e5b7a0ad0df9",
|
| 207 |
+
"metadata": {},
|
| 208 |
+
"outputs": [
|
| 209 |
+
{
|
| 210 |
+
"data": {
|
| 211 |
+
"application/vnd.jupyter.widget-view+json": {
|
| 212 |
+
"model_id": "d04b28ff3e8246dc803a95bb4f15d3c2",
|
| 213 |
+
"version_major": 2,
|
| 214 |
+
"version_minor": 0
|
| 215 |
+
},
|
| 216 |
+
"text/plain": [
|
| 217 |
+
"tokenizer_config.json: 0%| | 0.00/7.51k [00:00<?, ?B/s]"
|
| 218 |
+
]
|
| 219 |
+
},
|
| 220 |
+
"metadata": {},
|
| 221 |
+
"output_type": "display_data"
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"data": {
|
| 225 |
+
"application/vnd.jupyter.widget-view+json": {
|
| 226 |
+
"model_id": "29dd2c2cf11140d5b967ecfc19fe2c68",
|
| 227 |
+
"version_major": 2,
|
| 228 |
+
"version_minor": 0
|
| 229 |
+
},
|
| 230 |
+
"text/plain": [
|
| 231 |
+
"vocab.json: 0%| | 0.00/798k [00:00<?, ?B/s]"
|
| 232 |
+
]
|
| 233 |
+
},
|
| 234 |
+
"metadata": {},
|
| 235 |
+
"output_type": "display_data"
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"data": {
|
| 239 |
+
"application/vnd.jupyter.widget-view+json": {
|
| 240 |
+
"model_id": "14a2f9cd8d0e4c7faef69ebe828fb142",
|
| 241 |
+
"version_major": 2,
|
| 242 |
+
"version_minor": 0
|
| 243 |
+
},
|
| 244 |
+
"text/plain": [
|
| 245 |
+
"merges.txt: 0%| | 0.00/456k [00:00<?, ?B/s]"
|
| 246 |
+
]
|
| 247 |
+
},
|
| 248 |
+
"metadata": {},
|
| 249 |
+
"output_type": "display_data"
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"data": {
|
| 253 |
+
"application/vnd.jupyter.widget-view+json": {
|
| 254 |
+
"model_id": "fd232cd0227c48fa8923669b8afa40b8",
|
| 255 |
+
"version_major": 2,
|
| 256 |
+
"version_minor": 0
|
| 257 |
+
},
|
| 258 |
+
"text/plain": [
|
| 259 |
+
"tokenizer.json: 0%| | 0.00/2.12M [00:00<?, ?B/s]"
|
| 260 |
+
]
|
| 261 |
+
},
|
| 262 |
+
"metadata": {},
|
| 263 |
+
"output_type": "display_data"
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"data": {
|
| 267 |
+
"application/vnd.jupyter.widget-view+json": {
|
| 268 |
+
"model_id": "62b052078fca48e2ae4a3b928671c3ff",
|
| 269 |
+
"version_major": 2,
|
| 270 |
+
"version_minor": 0
|
| 271 |
+
},
|
| 272 |
+
"text/plain": [
|
| 273 |
+
"added_tokens.json: 0%| | 0.00/1.08k [00:00<?, ?B/s]"
|
| 274 |
+
]
|
| 275 |
+
},
|
| 276 |
+
"metadata": {},
|
| 277 |
+
"output_type": "display_data"
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"data": {
|
| 281 |
+
"application/vnd.jupyter.widget-view+json": {
|
| 282 |
+
"model_id": "e49797476ec14ef99a1161a673030aa4",
|
| 283 |
+
"version_major": 2,
|
| 284 |
+
"version_minor": 0
|
| 285 |
+
},
|
| 286 |
+
"text/plain": [
|
| 287 |
+
"special_tokens_map.json: 0%| | 0.00/587 [00:00<?, ?B/s]"
|
| 288 |
+
]
|
| 289 |
+
},
|
| 290 |
+
"metadata": {},
|
| 291 |
+
"output_type": "display_data"
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"data": {
|
| 295 |
+
"application/vnd.jupyter.widget-view+json": {
|
| 296 |
+
"model_id": "1a52317f238f496892f43e940b0f88f5",
|
| 297 |
+
"version_major": 2,
|
| 298 |
+
"version_minor": 0
|
| 299 |
+
},
|
| 300 |
+
"text/plain": [
|
| 301 |
+
"model.safetensors.index.json: 0%| | 0.00/24.7k [00:00<?, ?B/s]"
|
| 302 |
+
]
|
| 303 |
+
},
|
| 304 |
+
"metadata": {},
|
| 305 |
+
"output_type": "display_data"
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"data": {
|
| 309 |
+
"application/vnd.jupyter.widget-view+json": {
|
| 310 |
+
"model_id": "756caaf635bf477e815b198d3c1a4bae",
|
| 311 |
+
"version_major": 2,
|
| 312 |
+
"version_minor": 0
|
| 313 |
+
},
|
| 314 |
+
"text/plain": [
|
| 315 |
+
"Downloading shards: 0%| | 0/2 [00:00<?, ?it/s]"
|
| 316 |
+
]
|
| 317 |
+
},
|
| 318 |
+
"metadata": {},
|
| 319 |
+
"output_type": "display_data"
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"data": {
|
| 323 |
+
"application/vnd.jupyter.widget-view+json": {
|
| 324 |
+
"model_id": "20ee3df9a2794587acfa73cadb03a39f",
|
| 325 |
+
"version_major": 2,
|
| 326 |
+
"version_minor": 0
|
| 327 |
+
},
|
| 328 |
+
"text/plain": [
|
| 329 |
+
"model-00001-of-00002.safetensors: 0%| | 0.00/4.98G [00:00<?, ?B/s]"
|
| 330 |
+
]
|
| 331 |
+
},
|
| 332 |
+
"metadata": {},
|
| 333 |
+
"output_type": "display_data"
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"ename": "KeyboardInterrupt",
|
| 337 |
+
"evalue": "",
|
| 338 |
+
"output_type": "error",
|
| 339 |
+
"traceback": [
|
| 340 |
+
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
|
| 341 |
+
"\u001b[0;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)",
|
| 342 |
+
"Cell \u001b[0;32mIn[18], line 5\u001b[0m\n\u001b[1;32m 2\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtransformers\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m AutoTokenizer, AutoModel\n\u001b[1;32m 4\u001b[0m tokenizer \u001b[38;5;241m=\u001b[39m AutoTokenizer\u001b[38;5;241m.\u001b[39mfrom_pretrained(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mOpenOpenAI/checkpoint-2500\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m----> 5\u001b[0m model \u001b[38;5;241m=\u001b[39m \u001b[43mAutoModel\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfrom_pretrained\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mOpenOpenAI/checkpoint-2500\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\n",
|
| 343 |
+
"File \u001b[0;32m/usr/local/lib/python3.10/dist-packages/transformers/models/auto/auto_factory.py:564\u001b[0m, in \u001b[0;36m_BaseAutoModelClass.from_pretrained\u001b[0;34m(cls, pretrained_model_name_or_path, *model_args, **kwargs)\u001b[0m\n\u001b[1;32m 562\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m \u001b[38;5;28mtype\u001b[39m(config) \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mcls\u001b[39m\u001b[38;5;241m.\u001b[39m_model_mapping\u001b[38;5;241m.\u001b[39mkeys():\n\u001b[1;32m 563\u001b[0m model_class \u001b[38;5;241m=\u001b[39m _get_model_class(config, \u001b[38;5;28mcls\u001b[39m\u001b[38;5;241m.\u001b[39m_model_mapping)\n\u001b[0;32m--> 564\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mmodel_class\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfrom_pretrained\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 565\u001b[0m \u001b[43m \u001b[49m\u001b[43mpretrained_model_name_or_path\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mmodel_args\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mconfig\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mconfig\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mhub_kwargs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\n\u001b[1;32m 566\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 567\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\n\u001b[1;32m 568\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mUnrecognized configuration class \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mconfig\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__class__\u001b[39m\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m for this kind of AutoModel: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;28mcls\u001b[39m\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__name__\u001b[39m\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m.\u001b[39m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 569\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mModel type should be one of \u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m, \u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;241m.\u001b[39mjoin(c\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__name__\u001b[39m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mfor\u001b[39;00m\u001b[38;5;250m \u001b[39mc\u001b[38;5;250m \u001b[39m\u001b[38;5;129;01min\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28mcls\u001b[39m\u001b[38;5;241m.\u001b[39m_model_mapping\u001b[38;5;241m.\u001b[39mkeys())\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m.\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 570\u001b[0m )\n",
|
| 344 |
+
"File \u001b[0;32m/usr/local/lib/python3.10/dist-packages/transformers/modeling_utils.py:3658\u001b[0m, in \u001b[0;36mPreTrainedModel.from_pretrained\u001b[0;34m(cls, pretrained_model_name_or_path, config, cache_dir, ignore_mismatched_sizes, force_download, local_files_only, token, revision, use_safetensors, *model_args, **kwargs)\u001b[0m\n\u001b[1;32m 3655\u001b[0m \u001b[38;5;66;03m# We'll need to download and cache each checkpoint shard if the checkpoint is sharded.\u001b[39;00m\n\u001b[1;32m 3656\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m is_sharded:\n\u001b[1;32m 3657\u001b[0m \u001b[38;5;66;03m# resolved_archive_file becomes a list of files that point to the different checkpoint shards in this case.\u001b[39;00m\n\u001b[0;32m-> 3658\u001b[0m resolved_archive_file, sharded_metadata \u001b[38;5;241m=\u001b[39m \u001b[43mget_checkpoint_shard_files\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 3659\u001b[0m \u001b[43m \u001b[49m\u001b[43mpretrained_model_name_or_path\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 3660\u001b[0m \u001b[43m \u001b[49m\u001b[43mresolved_archive_file\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 3661\u001b[0m \u001b[43m \u001b[49m\u001b[43mcache_dir\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcache_dir\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 3662\u001b[0m \u001b[43m \u001b[49m\u001b[43mforce_download\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mforce_download\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 3663\u001b[0m \u001b[43m \u001b[49m\u001b[43mproxies\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mproxies\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 3664\u001b[0m \u001b[43m \u001b[49m\u001b[43mresume_download\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mresume_download\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 3665\u001b[0m \u001b[43m \u001b[49m\u001b[43mlocal_files_only\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mlocal_files_only\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 3666\u001b[0m \u001b[43m \u001b[49m\u001b[43mtoken\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtoken\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 3667\u001b[0m \u001b[43m \u001b[49m\u001b[43muser_agent\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43muser_agent\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 3668\u001b[0m \u001b[43m \u001b[49m\u001b[43mrevision\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrevision\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 3669\u001b[0m \u001b[43m \u001b[49m\u001b[43msubfolder\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43msubfolder\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 3670\u001b[0m \u001b[43m \u001b[49m\u001b[43m_commit_hash\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcommit_hash\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 3671\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 3673\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m (\n\u001b[1;32m 3674\u001b[0m is_safetensors_available()\n\u001b[1;32m 3675\u001b[0m \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(resolved_archive_file, \u001b[38;5;28mstr\u001b[39m)\n\u001b[1;32m 3676\u001b[0m \u001b[38;5;129;01mand\u001b[39;00m resolved_archive_file\u001b[38;5;241m.\u001b[39mendswith(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m.safetensors\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m 3677\u001b[0m ):\n\u001b[1;32m 3678\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m safe_open(resolved_archive_file, framework\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mpt\u001b[39m\u001b[38;5;124m\"\u001b[39m) \u001b[38;5;28;01mas\u001b[39;00m f:\n",
|
| 345 |
+
"File \u001b[0;32m/usr/local/lib/python3.10/dist-packages/transformers/utils/hub.py:1079\u001b[0m, in \u001b[0;36mget_checkpoint_shard_files\u001b[0;34m(pretrained_model_name_or_path, index_filename, cache_dir, force_download, proxies, resume_download, local_files_only, token, user_agent, revision, subfolder, _commit_hash, **deprecated_kwargs)\u001b[0m\n\u001b[1;32m 1076\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m shard_filename \u001b[38;5;129;01min\u001b[39;00m tqdm(shard_filenames, desc\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mDownloading shards\u001b[39m\u001b[38;5;124m\"\u001b[39m, disable\u001b[38;5;241m=\u001b[39m\u001b[38;5;129;01mnot\u001b[39;00m show_progress_bar):\n\u001b[1;32m 1077\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m 1078\u001b[0m \u001b[38;5;66;03m# Load from URL\u001b[39;00m\n\u001b[0;32m-> 1079\u001b[0m cached_filename \u001b[38;5;241m=\u001b[39m \u001b[43mcached_file\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 1080\u001b[0m \u001b[43m \u001b[49m\u001b[43mpretrained_model_name_or_path\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1081\u001b[0m \u001b[43m \u001b[49m\u001b[43mshard_filename\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1082\u001b[0m \u001b[43m \u001b[49m\u001b[43mcache_dir\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcache_dir\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1083\u001b[0m \u001b[43m \u001b[49m\u001b[43mforce_download\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mforce_download\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1084\u001b[0m \u001b[43m \u001b[49m\u001b[43mproxies\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mproxies\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1085\u001b[0m \u001b[43m \u001b[49m\u001b[43mresume_download\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mresume_download\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1086\u001b[0m \u001b[43m \u001b[49m\u001b[43mlocal_files_only\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mlocal_files_only\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1087\u001b[0m \u001b[43m \u001b[49m\u001b[43mtoken\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtoken\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1088\u001b[0m \u001b[43m \u001b[49m\u001b[43muser_agent\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43muser_agent\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1089\u001b[0m \u001b[43m \u001b[49m\u001b[43mrevision\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrevision\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1090\u001b[0m \u001b[43m \u001b[49m\u001b[43msubfolder\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43msubfolder\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1091\u001b[0m \u001b[43m \u001b[49m\u001b[43m_commit_hash\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m_commit_hash\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1092\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1093\u001b[0m \u001b[38;5;66;03m# We have already dealt with RepositoryNotFoundError and RevisionNotFoundError when getting the index, so\u001b[39;00m\n\u001b[1;32m 1094\u001b[0m \u001b[38;5;66;03m# we don't have to catch them here.\u001b[39;00m\n\u001b[1;32m 1095\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m EntryNotFoundError:\n",
|
| 346 |
+
"File \u001b[0;32m/usr/local/lib/python3.10/dist-packages/transformers/utils/hub.py:402\u001b[0m, in \u001b[0;36mcached_file\u001b[0;34m(path_or_repo_id, filename, cache_dir, force_download, resume_download, proxies, token, revision, local_files_only, subfolder, repo_type, user_agent, _raise_exceptions_for_gated_repo, _raise_exceptions_for_missing_entries, _raise_exceptions_for_connection_errors, _commit_hash, **deprecated_kwargs)\u001b[0m\n\u001b[1;32m 399\u001b[0m user_agent \u001b[38;5;241m=\u001b[39m http_user_agent(user_agent)\n\u001b[1;32m 400\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m 401\u001b[0m \u001b[38;5;66;03m# Load from URL or cache if already cached\u001b[39;00m\n\u001b[0;32m--> 402\u001b[0m resolved_file \u001b[38;5;241m=\u001b[39m \u001b[43mhf_hub_download\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 403\u001b[0m \u001b[43m \u001b[49m\u001b[43mpath_or_repo_id\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 404\u001b[0m \u001b[43m \u001b[49m\u001b[43mfilename\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 405\u001b[0m \u001b[43m \u001b[49m\u001b[43msubfolder\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mif\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43mlen\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43msubfolder\u001b[49m\u001b[43m)\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m==\u001b[39;49m\u001b[43m \u001b[49m\u001b[38;5;241;43m0\u001b[39;49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01melse\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43msubfolder\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 406\u001b[0m \u001b[43m \u001b[49m\u001b[43mrepo_type\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrepo_type\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 407\u001b[0m \u001b[43m \u001b[49m\u001b[43mrevision\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrevision\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 408\u001b[0m \u001b[43m \u001b[49m\u001b[43mcache_dir\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcache_dir\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 409\u001b[0m \u001b[43m \u001b[49m\u001b[43muser_agent\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43muser_agent\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 410\u001b[0m \u001b[43m \u001b[49m\u001b[43mforce_download\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mforce_download\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 411\u001b[0m \u001b[43m \u001b[49m\u001b[43mproxies\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mproxies\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 412\u001b[0m \u001b[43m \u001b[49m\u001b[43mresume_download\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mresume_download\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 413\u001b[0m \u001b[43m \u001b[49m\u001b[43mtoken\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtoken\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 414\u001b[0m \u001b[43m \u001b[49m\u001b[43mlocal_files_only\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mlocal_files_only\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 415\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 416\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m GatedRepoError \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m 417\u001b[0m resolved_file \u001b[38;5;241m=\u001b[39m _get_cache_file_to_return(path_or_repo_id, full_filename, cache_dir, revision)\n",
|
| 347 |
+
"File \u001b[0;32m/usr/local/lib/python3.10/dist-packages/huggingface_hub/utils/_deprecation.py:101\u001b[0m, in \u001b[0;36m_deprecate_arguments.<locals>._inner_deprecate_positional_args.<locals>.inner_f\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 99\u001b[0m message \u001b[38;5;241m+\u001b[39m\u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;241m+\u001b[39m custom_message\n\u001b[1;32m 100\u001b[0m warnings\u001b[38;5;241m.\u001b[39mwarn(message, \u001b[38;5;167;01mFutureWarning\u001b[39;00m)\n\u001b[0;32m--> 101\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mf\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
|
| 348 |
+
"File \u001b[0;32m/usr/local/lib/python3.10/dist-packages/huggingface_hub/utils/_validators.py:114\u001b[0m, in \u001b[0;36mvalidate_hf_hub_args.<locals>._inner_fn\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 111\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m check_use_auth_token:\n\u001b[1;32m 112\u001b[0m kwargs \u001b[38;5;241m=\u001b[39m smoothly_deprecate_use_auth_token(fn_name\u001b[38;5;241m=\u001b[39mfn\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__name__\u001b[39m, has_token\u001b[38;5;241m=\u001b[39mhas_token, kwargs\u001b[38;5;241m=\u001b[39mkwargs)\n\u001b[0;32m--> 114\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfn\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
|
| 349 |
+
"File \u001b[0;32m/usr/local/lib/python3.10/dist-packages/huggingface_hub/file_download.py:1240\u001b[0m, in \u001b[0;36mhf_hub_download\u001b[0;34m(repo_id, filename, subfolder, repo_type, revision, library_name, library_version, cache_dir, local_dir, user_agent, force_download, proxies, etag_timeout, token, local_files_only, headers, endpoint, legacy_cache_layout, resume_download, force_filename, local_dir_use_symlinks)\u001b[0m\n\u001b[1;32m 1220\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m _hf_hub_download_to_local_dir(\n\u001b[1;32m 1221\u001b[0m \u001b[38;5;66;03m# Destination\u001b[39;00m\n\u001b[1;32m 1222\u001b[0m local_dir\u001b[38;5;241m=\u001b[39mlocal_dir,\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 1237\u001b[0m local_files_only\u001b[38;5;241m=\u001b[39mlocal_files_only,\n\u001b[1;32m 1238\u001b[0m )\n\u001b[1;32m 1239\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 1240\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43m_hf_hub_download_to_cache_dir\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 1241\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;66;43;03m# Destination\u001b[39;49;00m\n\u001b[1;32m 1242\u001b[0m \u001b[43m \u001b[49m\u001b[43mcache_dir\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcache_dir\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1243\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;66;43;03m# File info\u001b[39;49;00m\n\u001b[1;32m 1244\u001b[0m \u001b[43m \u001b[49m\u001b[43mrepo_id\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrepo_id\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1245\u001b[0m \u001b[43m \u001b[49m\u001b[43mfilename\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mfilename\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1246\u001b[0m \u001b[43m \u001b[49m\u001b[43mrepo_type\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrepo_type\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1247\u001b[0m \u001b[43m \u001b[49m\u001b[43mrevision\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrevision\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1248\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;66;43;03m# HTTP info\u001b[39;49;00m\n\u001b[1;32m 1249\u001b[0m \u001b[43m \u001b[49m\u001b[43mendpoint\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mendpoint\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1250\u001b[0m \u001b[43m \u001b[49m\u001b[43metag_timeout\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43metag_timeout\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1251\u001b[0m \u001b[43m \u001b[49m\u001b[43mheaders\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mheaders\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1252\u001b[0m \u001b[43m \u001b[49m\u001b[43mproxies\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mproxies\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1253\u001b[0m \u001b[43m \u001b[49m\u001b[43mtoken\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtoken\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1254\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;66;43;03m# Additional options\u001b[39;49;00m\n\u001b[1;32m 1255\u001b[0m \u001b[43m \u001b[49m\u001b[43mlocal_files_only\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mlocal_files_only\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1256\u001b[0m \u001b[43m \u001b[49m\u001b[43mforce_download\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mforce_download\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1257\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n",
|
| 350 |
+
"File \u001b[0;32m/usr/local/lib/python3.10/dist-packages/huggingface_hub/file_download.py:1389\u001b[0m, in \u001b[0;36m_hf_hub_download_to_cache_dir\u001b[0;34m(cache_dir, repo_id, filename, repo_type, revision, endpoint, etag_timeout, headers, proxies, token, local_files_only, force_download)\u001b[0m\n\u001b[1;32m 1387\u001b[0m Path(lock_path)\u001b[38;5;241m.\u001b[39mparent\u001b[38;5;241m.\u001b[39mmkdir(parents\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m, exist_ok\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m)\n\u001b[1;32m 1388\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m WeakFileLock(lock_path):\n\u001b[0;32m-> 1389\u001b[0m \u001b[43m_download_to_tmp_and_move\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 1390\u001b[0m \u001b[43m \u001b[49m\u001b[43mincomplete_path\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mPath\u001b[49m\u001b[43m(\u001b[49m\u001b[43mblob_path\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m+\u001b[39;49m\u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43m.incomplete\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1391\u001b[0m \u001b[43m \u001b[49m\u001b[43mdestination_path\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mPath\u001b[49m\u001b[43m(\u001b[49m\u001b[43mblob_path\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1392\u001b[0m \u001b[43m \u001b[49m\u001b[43murl_to_download\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43murl_to_download\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1393\u001b[0m \u001b[43m \u001b[49m\u001b[43mproxies\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mproxies\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1394\u001b[0m \u001b[43m \u001b[49m\u001b[43mheaders\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mheaders\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1395\u001b[0m \u001b[43m \u001b[49m\u001b[43mexpected_size\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mexpected_size\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1396\u001b[0m \u001b[43m \u001b[49m\u001b[43mfilename\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mfilename\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1397\u001b[0m \u001b[43m \u001b[49m\u001b[43mforce_download\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mforce_download\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1398\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1399\u001b[0m _create_symlink(blob_path, pointer_path, new_blob\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m)\n\u001b[1;32m 1401\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m pointer_path\n",
|
| 351 |
+
"File \u001b[0;32m/usr/local/lib/python3.10/dist-packages/huggingface_hub/file_download.py:1915\u001b[0m, in \u001b[0;36m_download_to_tmp_and_move\u001b[0;34m(incomplete_path, destination_path, url_to_download, proxies, headers, expected_size, filename, force_download)\u001b[0m\n\u001b[1;32m 1912\u001b[0m _check_disk_space(expected_size, incomplete_path\u001b[38;5;241m.\u001b[39mparent)\n\u001b[1;32m 1913\u001b[0m _check_disk_space(expected_size, destination_path\u001b[38;5;241m.\u001b[39mparent)\n\u001b[0;32m-> 1915\u001b[0m \u001b[43mhttp_get\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 1916\u001b[0m \u001b[43m \u001b[49m\u001b[43murl_to_download\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1917\u001b[0m \u001b[43m \u001b[49m\u001b[43mf\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1918\u001b[0m \u001b[43m \u001b[49m\u001b[43mproxies\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mproxies\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1919\u001b[0m \u001b[43m \u001b[49m\u001b[43mresume_size\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mresume_size\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1920\u001b[0m \u001b[43m \u001b[49m\u001b[43mheaders\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mheaders\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1921\u001b[0m \u001b[43m \u001b[49m\u001b[43mexpected_size\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mexpected_size\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1922\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1924\u001b[0m logger\u001b[38;5;241m.\u001b[39minfo(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mDownload complete. Moving file to \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mdestination_path\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m 1925\u001b[0m _chmod_and_move(incomplete_path, destination_path)\n",
|
| 352 |
+
"File \u001b[0;32m/usr/local/lib/python3.10/dist-packages/huggingface_hub/file_download.py:549\u001b[0m, in \u001b[0;36mhttp_get\u001b[0;34m(url, temp_file, proxies, resume_size, headers, expected_size, displayed_filename, _nb_retries, _tqdm_bar)\u001b[0m\n\u001b[1;32m 547\u001b[0m new_resume_size \u001b[38;5;241m=\u001b[39m resume_size\n\u001b[1;32m 548\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 549\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m chunk \u001b[38;5;129;01min\u001b[39;00m r\u001b[38;5;241m.\u001b[39miter_content(chunk_size\u001b[38;5;241m=\u001b[39mDOWNLOAD_CHUNK_SIZE):\n\u001b[1;32m 550\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m chunk: \u001b[38;5;66;03m# filter out keep-alive new chunks\u001b[39;00m\n\u001b[1;32m 551\u001b[0m progress\u001b[38;5;241m.\u001b[39mupdate(\u001b[38;5;28mlen\u001b[39m(chunk))\n",
|
| 353 |
+
"File \u001b[0;32m/usr/local/lib/python3.10/dist-packages/requests/models.py:820\u001b[0m, in \u001b[0;36mResponse.iter_content.<locals>.generate\u001b[0;34m()\u001b[0m\n\u001b[1;32m 818\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mhasattr\u001b[39m(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mraw, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mstream\u001b[39m\u001b[38;5;124m\"\u001b[39m):\n\u001b[1;32m 819\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 820\u001b[0m \u001b[38;5;28;01myield from\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mraw\u001b[38;5;241m.\u001b[39mstream(chunk_size, decode_content\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m)\n\u001b[1;32m 821\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m ProtocolError \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m 822\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m ChunkedEncodingError(e)\n",
|
| 354 |
+
"File \u001b[0;32m/usr/local/lib/python3.10/dist-packages/urllib3/response.py:628\u001b[0m, in \u001b[0;36mHTTPResponse.stream\u001b[0;34m(self, amt, decode_content)\u001b[0m\n\u001b[1;32m 626\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 627\u001b[0m \u001b[38;5;28;01mwhile\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m is_fp_closed(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_fp):\n\u001b[0;32m--> 628\u001b[0m data \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mread\u001b[49m\u001b[43m(\u001b[49m\u001b[43mamt\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mamt\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mdecode_content\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mdecode_content\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 630\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m data:\n\u001b[1;32m 631\u001b[0m \u001b[38;5;28;01myield\u001b[39;00m data\n",
|
| 355 |
+
"File \u001b[0;32m/usr/local/lib/python3.10/dist-packages/urllib3/response.py:567\u001b[0m, in \u001b[0;36mHTTPResponse.read\u001b[0;34m(self, amt, decode_content, cache_content)\u001b[0m\n\u001b[1;32m 564\u001b[0m fp_closed \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mgetattr\u001b[39m(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_fp, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mclosed\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;28;01mFalse\u001b[39;00m)\n\u001b[1;32m 566\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_error_catcher():\n\u001b[0;32m--> 567\u001b[0m data \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_fp_read\u001b[49m\u001b[43m(\u001b[49m\u001b[43mamt\u001b[49m\u001b[43m)\u001b[49m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m fp_closed \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;124mb\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 568\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m amt \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m 569\u001b[0m flush_decoder \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mTrue\u001b[39;00m\n",
|
| 356 |
+
"File \u001b[0;32m/usr/local/lib/python3.10/dist-packages/urllib3/response.py:533\u001b[0m, in \u001b[0;36mHTTPResponse._fp_read\u001b[0;34m(self, amt)\u001b[0m\n\u001b[1;32m 530\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m buffer\u001b[38;5;241m.\u001b[39mgetvalue()\n\u001b[1;32m 531\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 532\u001b[0m \u001b[38;5;66;03m# StringIO doesn't like amt=None\u001b[39;00m\n\u001b[0;32m--> 533\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_fp\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mread\u001b[49m\u001b[43m(\u001b[49m\u001b[43mamt\u001b[49m\u001b[43m)\u001b[49m \u001b[38;5;28;01mif\u001b[39;00m amt \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_fp\u001b[38;5;241m.\u001b[39mread()\n",
|
| 357 |
+
"File \u001b[0;32m/usr/lib/python3.10/http/client.py:466\u001b[0m, in \u001b[0;36mHTTPResponse.read\u001b[0;34m(self, amt)\u001b[0m\n\u001b[1;32m 463\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mlength \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;129;01mand\u001b[39;00m amt \u001b[38;5;241m>\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mlength:\n\u001b[1;32m 464\u001b[0m \u001b[38;5;66;03m# clip the read to the \"end of response\"\u001b[39;00m\n\u001b[1;32m 465\u001b[0m amt \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mlength\n\u001b[0;32m--> 466\u001b[0m s \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfp\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mread\u001b[49m\u001b[43m(\u001b[49m\u001b[43mamt\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 467\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m s \u001b[38;5;129;01mand\u001b[39;00m amt:\n\u001b[1;32m 468\u001b[0m \u001b[38;5;66;03m# Ideally, we would raise IncompleteRead if the content-length\u001b[39;00m\n\u001b[1;32m 469\u001b[0m \u001b[38;5;66;03m# wasn't satisfied, but it might break compatibility.\u001b[39;00m\n\u001b[1;32m 470\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_close_conn()\n",
|
| 358 |
+
"File \u001b[0;32m/usr/lib/python3.10/socket.py:705\u001b[0m, in \u001b[0;36mSocketIO.readinto\u001b[0;34m(self, b)\u001b[0m\n\u001b[1;32m 703\u001b[0m \u001b[38;5;28;01mwhile\u001b[39;00m \u001b[38;5;28;01mTrue\u001b[39;00m:\n\u001b[1;32m 704\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 705\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_sock\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mrecv_into\u001b[49m\u001b[43m(\u001b[49m\u001b[43mb\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 706\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m timeout:\n\u001b[1;32m 707\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_timeout_occurred \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mTrue\u001b[39;00m\n",
|
| 359 |
+
"File \u001b[0;32m/usr/lib/python3.10/ssl.py:1274\u001b[0m, in \u001b[0;36mSSLSocket.recv_into\u001b[0;34m(self, buffer, nbytes, flags)\u001b[0m\n\u001b[1;32m 1270\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m flags \u001b[38;5;241m!=\u001b[39m \u001b[38;5;241m0\u001b[39m:\n\u001b[1;32m 1271\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\n\u001b[1;32m 1272\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mnon-zero flags not allowed in calls to recv_into() on \u001b[39m\u001b[38;5;132;01m%s\u001b[39;00m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;241m%\u001b[39m\n\u001b[1;32m 1273\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__class__\u001b[39m)\n\u001b[0;32m-> 1274\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mread\u001b[49m\u001b[43m(\u001b[49m\u001b[43mnbytes\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mbuffer\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1275\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 1276\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28msuper\u001b[39m()\u001b[38;5;241m.\u001b[39mrecv_into(buffer, nbytes, flags)\n",
|
| 360 |
+
"File \u001b[0;32m/usr/lib/python3.10/ssl.py:1130\u001b[0m, in \u001b[0;36mSSLSocket.read\u001b[0;34m(self, len, buffer)\u001b[0m\n\u001b[1;32m 1128\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m 1129\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m buffer \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[0;32m-> 1130\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_sslobj\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mread\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mlen\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mbuffer\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1131\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 1132\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_sslobj\u001b[38;5;241m.\u001b[39mread(\u001b[38;5;28mlen\u001b[39m)\n",
|
| 361 |
+
"\u001b[0;31mKeyboardInterrupt\u001b[0m: "
|
| 362 |
+
]
|
| 363 |
+
}
|
| 364 |
+
],
|
| 365 |
+
"source": [
|
| 366 |
+
"# Load model directly\n",
|
| 367 |
+
"from transformers import AutoTokenizer, AutoModel\n",
|
| 368 |
+
"\n",
|
| 369 |
+
"tokenizer = AutoTokenizer.from_pretrained(\"OpenOpenAI/checkpoint-2500\")\n",
|
| 370 |
+
"model = AutoModel.from_pretrained(\"OpenOpenAI/checkpoint-2500\")"
|
| 371 |
+
]
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"cell_type": "code",
|
| 375 |
+
"execution_count": null,
|
| 376 |
+
"id": "d3443f20-cd0e-4fa0-97ab-a69f73c72be6",
|
| 377 |
+
"metadata": {},
|
| 378 |
+
"outputs": [],
|
| 379 |
+
"source": []
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"cell_type": "code",
|
| 383 |
+
"execution_count": null,
|
| 384 |
+
"id": "65b919ca-4d3c-49bf-a0bc-4240defb84d1",
|
| 385 |
+
"metadata": {},
|
| 386 |
+
"outputs": [],
|
| 387 |
+
"source": []
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"cell_type": "code",
|
| 391 |
+
"execution_count": null,
|
| 392 |
+
"id": "5000a1a2-a562-403e-af50-9477a3ecbcbb",
|
| 393 |
+
"metadata": {},
|
| 394 |
+
"outputs": [
|
| 395 |
+
{
|
| 396 |
+
"data": {
|
| 397 |
+
"application/vnd.jupyter.widget-view+json": {
|
| 398 |
+
"model_id": "ce2c8a458e2f48209383c557f58f1e5d",
|
| 399 |
+
"version_major": 2,
|
| 400 |
+
"version_minor": 0
|
| 401 |
+
},
|
| 402 |
+
"text/plain": [
|
| 403 |
+
"config.json: 0%| | 0.00/743 [00:00<?, ?B/s]"
|
| 404 |
+
]
|
| 405 |
+
},
|
| 406 |
+
"metadata": {},
|
| 407 |
+
"output_type": "display_data"
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"data": {
|
| 411 |
+
"application/vnd.jupyter.widget-view+json": {
|
| 412 |
+
"model_id": "eae84f82c9304d9f8af556958830f436",
|
| 413 |
+
"version_major": 2,
|
| 414 |
+
"version_minor": 0
|
| 415 |
+
},
|
| 416 |
+
"text/plain": [
|
| 417 |
+
"Downloading shards: 0%| | 0/2 [00:00<?, ?it/s]"
|
| 418 |
+
]
|
| 419 |
+
},
|
| 420 |
+
"metadata": {},
|
| 421 |
+
"output_type": "display_data"
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"data": {
|
| 425 |
+
"application/vnd.jupyter.widget-view+json": {
|
| 426 |
+
"model_id": "7b95d784fc494882852373c34cbd4019",
|
| 427 |
+
"version_major": 2,
|
| 428 |
+
"version_minor": 0
|
| 429 |
+
},
|
| 430 |
+
"text/plain": [
|
| 431 |
+
"model-00001-of-00002.safetensors: 5%|4 | 241M/4.98G [00:00<?, ?B/s]"
|
| 432 |
+
]
|
| 433 |
+
},
|
| 434 |
+
"metadata": {},
|
| 435 |
+
"output_type": "display_data"
|
| 436 |
+
}
|
| 437 |
+
],
|
| 438 |
+
"source": [
|
| 439 |
+
"# Load model directly\n",
|
| 440 |
+
"from transformers import AutoTokenizer, AutoModel\n",
|
| 441 |
+
"\n",
|
| 442 |
+
"tokenizer = AutoTokenizer.from_pretrained(\"OpenOpenAI/checkpoint-2500\")\n",
|
| 443 |
+
"model = AutoModel.from_pretrained(\"OpenOpenAI/checkpoint-2500\")"
|
| 444 |
+
]
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"cell_type": "code",
|
| 448 |
+
"execution_count": null,
|
| 449 |
+
"id": "0f8a691a-15be-4ce2-9ea1-8758471f5824",
|
| 450 |
+
"metadata": {},
|
| 451 |
+
"outputs": [],
|
| 452 |
+
"source": []
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"cell_type": "code",
|
| 456 |
+
"execution_count": 13,
|
| 457 |
+
"id": "9da6361a-e291-4a91-a942-676f84292c43",
|
| 458 |
+
"metadata": {},
|
| 459 |
+
"outputs": [
|
| 460 |
+
{
|
| 461 |
+
"ename": "OSError",
|
| 462 |
+
"evalue": "Can't load tokenizer for 'OpenOpenAI/checkpoint-2500'. If you were trying to load it from 'https://huggingface.co/models', make sure you don't have a local directory with the same name. Otherwise, make sure 'OpenOpenAI/checkpoint-2500' is the correct path to a directory containing all relevant files for a CodeGenTokenizerFast tokenizer.",
|
| 463 |
+
"output_type": "error",
|
| 464 |
+
"traceback": [
|
| 465 |
+
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
|
| 466 |
+
"\u001b[0;31mOSError\u001b[0m Traceback (most recent call last)",
|
| 467 |
+
"Cell \u001b[0;32mIn[13], line 5\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtransformers\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m AutoTokenizer, AutoModel\n\u001b[1;32m 3\u001b[0m model_name \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mOpenOpenAI/checkpoint-2500\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;66;03m# Replace with the correct path\u001b[39;00m\n\u001b[0;32m----> 5\u001b[0m tokenizer \u001b[38;5;241m=\u001b[39m \u001b[43mAutoTokenizer\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfrom_pretrained\u001b[49m\u001b[43m(\u001b[49m\u001b[43mmodel_name\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 6\u001b[0m model \u001b[38;5;241m=\u001b[39m AutoModel\u001b[38;5;241m.\u001b[39mfrom_pretrained(model_name)\n",
|
| 468 |
+
"File \u001b[0;32m/usr/local/lib/python3.10/dist-packages/transformers/models/auto/tokenization_auto.py:915\u001b[0m, in \u001b[0;36mAutoTokenizer.from_pretrained\u001b[0;34m(cls, pretrained_model_name_or_path, *inputs, **kwargs)\u001b[0m\n\u001b[1;32m 912\u001b[0m tokenizer_class_py, tokenizer_class_fast \u001b[38;5;241m=\u001b[39m TOKENIZER_MAPPING[\u001b[38;5;28mtype\u001b[39m(config)]\n\u001b[1;32m 914\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m tokenizer_class_fast \u001b[38;5;129;01mand\u001b[39;00m (use_fast \u001b[38;5;129;01mor\u001b[39;00m tokenizer_class_py \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m):\n\u001b[0;32m--> 915\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mtokenizer_class_fast\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfrom_pretrained\u001b[49m\u001b[43m(\u001b[49m\u001b[43mpretrained_model_name_or_path\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43minputs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 916\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 917\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m tokenizer_class_py \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n",
|
| 469 |
+
"File \u001b[0;32m/usr/local/lib/python3.10/dist-packages/transformers/tokenization_utils_base.py:2275\u001b[0m, in \u001b[0;36mPreTrainedTokenizerBase.from_pretrained\u001b[0;34m(cls, pretrained_model_name_or_path, cache_dir, force_download, local_files_only, token, revision, trust_remote_code, *init_inputs, **kwargs)\u001b[0m\n\u001b[1;32m 2272\u001b[0m \u001b[38;5;66;03m# If one passes a GGUF file path to `gguf_file` there is no need for this check as the tokenizer will be\u001b[39;00m\n\u001b[1;32m 2273\u001b[0m \u001b[38;5;66;03m# loaded directly from the GGUF file.\u001b[39;00m\n\u001b[1;32m 2274\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mall\u001b[39m(full_file_name \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;28;01mfor\u001b[39;00m full_file_name \u001b[38;5;129;01min\u001b[39;00m resolved_vocab_files\u001b[38;5;241m.\u001b[39mvalues()) \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m gguf_file:\n\u001b[0;32m-> 2275\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mEnvironmentError\u001b[39;00m(\n\u001b[1;32m 2276\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mCan\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mt load tokenizer for \u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mpretrained_model_name_or_path\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m. If you were trying to load it from \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 2277\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mhttps://huggingface.co/models\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m, make sure you don\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mt have a local directory with the same name. \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 2278\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mOtherwise, make sure \u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mpretrained_model_name_or_path\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m is the correct path to a directory \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 2279\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mcontaining all relevant files for a \u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;28mcls\u001b[39m\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__name__\u001b[39m\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m tokenizer.\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 2280\u001b[0m )\n\u001b[1;32m 2282\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m file_id, file_path \u001b[38;5;129;01min\u001b[39;00m vocab_files\u001b[38;5;241m.\u001b[39mitems():\n\u001b[1;32m 2283\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m file_id \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m resolved_vocab_files:\n",
|
| 470 |
+
"\u001b[0;31mOSError\u001b[0m: Can't load tokenizer for 'OpenOpenAI/checkpoint-2500'. If you were trying to load it from 'https://huggingface.co/models', make sure you don't have a local directory with the same name. Otherwise, make sure 'OpenOpenAI/checkpoint-2500' is the correct path to a directory containing all relevant files for a CodeGenTokenizerFast tokenizer."
|
| 471 |
+
]
|
| 472 |
+
}
|
| 473 |
+
],
|
| 474 |
+
"source": [
|
| 475 |
+
"from transformers import AutoTokenizer, AutoModel\n",
|
| 476 |
+
"\n",
|
| 477 |
+
"model_name = \"OpenOpenAI/checkpoint-2500\" # Replace with the correct path\n",
|
| 478 |
+
"\n",
|
| 479 |
+
"tokenizer = AutoTokenizer.from_pretrained(model_name)\n",
|
| 480 |
+
"model = AutoModel.from_pretrained(model_name)"
|
| 481 |
+
]
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"cell_type": "code",
|
| 485 |
+
"execution_count": null,
|
| 486 |
+
"id": "0da6e77a-bfb1-4e24-af67-1b76009f7289",
|
| 487 |
+
"metadata": {},
|
| 488 |
+
"outputs": [],
|
| 489 |
+
"source": []
|
| 490 |
+
}
|
| 491 |
+
],
|
| 492 |
+
"metadata": {
|
| 493 |
+
"kernelspec": {
|
| 494 |
+
"display_name": "Python 3 (ipykernel)",
|
| 495 |
+
"language": "python",
|
| 496 |
+
"name": "python3"
|
| 497 |
+
},
|
| 498 |
+
"language_info": {
|
| 499 |
+
"codemirror_mode": {
|
| 500 |
+
"name": "ipython",
|
| 501 |
+
"version": 3
|
| 502 |
+
},
|
| 503 |
+
"file_extension": ".py",
|
| 504 |
+
"mimetype": "text/x-python",
|
| 505 |
+
"name": "python",
|
| 506 |
+
"nbconvert_exporter": "python",
|
| 507 |
+
"pygments_lexer": "ipython3",
|
| 508 |
+
"version": "3.10.12"
|
| 509 |
+
}
|
| 510 |
+
},
|
| 511 |
+
"nbformat": 4,
|
| 512 |
+
"nbformat_minor": 5
|
| 513 |
+
}
|
.ipynb_checkpoints/added_tokens-checkpoint.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"\t\t": 50294,
|
| 3 |
+
"\t\t\t": 50293,
|
| 4 |
+
"\t\t\t\t": 50292,
|
| 5 |
+
"\t\t\t\t\t": 50291,
|
| 6 |
+
"\t\t\t\t\t\t": 50290,
|
| 7 |
+
"\t\t\t\t\t\t\t": 50289,
|
| 8 |
+
"\t\t\t\t\t\t\t\t": 50288,
|
| 9 |
+
"\t\t\t\t\t\t\t\t\t": 50287,
|
| 10 |
+
" ": 50286,
|
| 11 |
+
" ": 50285,
|
| 12 |
+
" ": 50284,
|
| 13 |
+
" ": 50283,
|
| 14 |
+
" ": 50282,
|
| 15 |
+
" ": 50281,
|
| 16 |
+
" ": 50280,
|
| 17 |
+
" ": 50279,
|
| 18 |
+
" ": 50278,
|
| 19 |
+
" ": 50277,
|
| 20 |
+
" ": 50276,
|
| 21 |
+
" ": 50275,
|
| 22 |
+
" ": 50274,
|
| 23 |
+
" ": 50273,
|
| 24 |
+
" ": 50272,
|
| 25 |
+
" ": 50271,
|
| 26 |
+
" ": 50270,
|
| 27 |
+
" ": 50269,
|
| 28 |
+
" ": 50268,
|
| 29 |
+
" ": 50267,
|
| 30 |
+
" ": 50266,
|
| 31 |
+
" ": 50265,
|
| 32 |
+
" ": 50264,
|
| 33 |
+
" ": 50263,
|
| 34 |
+
" ": 50262,
|
| 35 |
+
" ": 50261,
|
| 36 |
+
" ": 50260,
|
| 37 |
+
" ": 50259,
|
| 38 |
+
" ": 50258,
|
| 39 |
+
" ": 50257
|
| 40 |
+
}
|
Untitled.ipynb
ADDED
|
@@ -0,0 +1,593 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cells": [
|
| 3 |
+
{
|
| 4 |
+
"cell_type": "code",
|
| 5 |
+
"execution_count": 20,
|
| 6 |
+
"id": "88d5b164-4be8-4cce-b271-75c6de9e662a",
|
| 7 |
+
"metadata": {},
|
| 8 |
+
"outputs": [
|
| 9 |
+
{
|
| 10 |
+
"data": {
|
| 11 |
+
"text/plain": [
|
| 12 |
+
"PhiModel(\n",
|
| 13 |
+
" (embed_tokens): Embedding(51200, 2048)\n",
|
| 14 |
+
" (embed_dropout): Dropout(p=0.0, inplace=False)\n",
|
| 15 |
+
" (layers): ModuleList(\n",
|
| 16 |
+
" (0-23): 24 x PhiDecoderLayer(\n",
|
| 17 |
+
" (self_attn): PhiAttention(\n",
|
| 18 |
+
" (q_proj): Linear(in_features=2048, out_features=2048, bias=True)\n",
|
| 19 |
+
" (k_proj): Linear(in_features=2048, out_features=2048, bias=True)\n",
|
| 20 |
+
" (v_proj): Linear(in_features=2048, out_features=2048, bias=True)\n",
|
| 21 |
+
" (dense): Linear(in_features=2048, out_features=2048, bias=True)\n",
|
| 22 |
+
" (rotary_emb): PhiRotaryEmbedding()\n",
|
| 23 |
+
" )\n",
|
| 24 |
+
" (mlp): PhiMLP(\n",
|
| 25 |
+
" (activation_fn): NewGELUActivation()\n",
|
| 26 |
+
" (fc1): Linear(in_features=2048, out_features=8192, bias=True)\n",
|
| 27 |
+
" (fc2): Linear(in_features=8192, out_features=2048, bias=True)\n",
|
| 28 |
+
" )\n",
|
| 29 |
+
" (input_layernorm): LayerNorm((2048,), eps=1e-05, elementwise_affine=True)\n",
|
| 30 |
+
" (resid_dropout): Dropout(p=0.0, inplace=False)\n",
|
| 31 |
+
" )\n",
|
| 32 |
+
" )\n",
|
| 33 |
+
" (final_layernorm): LayerNorm((2048,), eps=1e-05, elementwise_affine=True)\n",
|
| 34 |
+
")"
|
| 35 |
+
]
|
| 36 |
+
},
|
| 37 |
+
"execution_count": 20,
|
| 38 |
+
"metadata": {},
|
| 39 |
+
"output_type": "execute_result"
|
| 40 |
+
}
|
| 41 |
+
],
|
| 42 |
+
"source": [
|
| 43 |
+
"from transformers import AutoModel, AutoTokenizer, AutoConfig\n",
|
| 44 |
+
"\n",
|
| 45 |
+
"# Specify the path to your checkpoint directory\n",
|
| 46 |
+
"checkpoint_dir = \"/workspace/OpenRLHF3/checkpoint/llama-3-8b-rlhf/iter_14\"\n",
|
| 47 |
+
"\n",
|
| 48 |
+
"# Load the model configuration\n",
|
| 49 |
+
"config = AutoConfig.from_pretrained(checkpoint_dir)\n",
|
| 50 |
+
"\n",
|
| 51 |
+
"# Load the tokenizer\n",
|
| 52 |
+
"tokenizer = AutoTokenizer.from_pretrained(checkpoint_dir)\n",
|
| 53 |
+
"\n",
|
| 54 |
+
"# Load the model using the safetensors files\n",
|
| 55 |
+
"model = AutoModel.from_pretrained(checkpoint_dir)\n",
|
| 56 |
+
"\n",
|
| 57 |
+
"# Set the model to evaluation mode\n",
|
| 58 |
+
"model.eval()\n",
|
| 59 |
+
"\n",
|
| 60 |
+
"# Now the model is ready to use for inference"
|
| 61 |
+
]
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"cell_type": "code",
|
| 65 |
+
"execution_count": 11,
|
| 66 |
+
"id": "3f4721b1-0853-47a0-88b4-7720a0ef79ee",
|
| 67 |
+
"metadata": {},
|
| 68 |
+
"outputs": [
|
| 69 |
+
{
|
| 70 |
+
"data": {
|
| 71 |
+
"application/vnd.jupyter.widget-view+json": {
|
| 72 |
+
"model_id": "3862f17dcf0d46998871e14b6324e47f",
|
| 73 |
+
"version_major": 2,
|
| 74 |
+
"version_minor": 0
|
| 75 |
+
},
|
| 76 |
+
"text/plain": [
|
| 77 |
+
"model-00001-of-00002.safetensors: 0%| | 0.00/4.98G [00:00<?, ?B/s]"
|
| 78 |
+
]
|
| 79 |
+
},
|
| 80 |
+
"metadata": {},
|
| 81 |
+
"output_type": "display_data"
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"data": {
|
| 85 |
+
"application/vnd.jupyter.widget-view+json": {
|
| 86 |
+
"model_id": "846214a9ecc446128aac3e409588581e",
|
| 87 |
+
"version_major": 2,
|
| 88 |
+
"version_minor": 0
|
| 89 |
+
},
|
| 90 |
+
"text/plain": [
|
| 91 |
+
"model-00002-of-00002.safetensors: 0%| | 0.00/269M [00:00<?, ?B/s]"
|
| 92 |
+
]
|
| 93 |
+
},
|
| 94 |
+
"metadata": {},
|
| 95 |
+
"output_type": "display_data"
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"data": {
|
| 99 |
+
"application/vnd.jupyter.widget-view+json": {
|
| 100 |
+
"model_id": "66f069e0e7bc4d5391170a352c323372",
|
| 101 |
+
"version_major": 2,
|
| 102 |
+
"version_minor": 0
|
| 103 |
+
},
|
| 104 |
+
"text/plain": [
|
| 105 |
+
"Upload 2 LFS files: 0%| | 0/2 [00:00<?, ?it/s]"
|
| 106 |
+
]
|
| 107 |
+
},
|
| 108 |
+
"metadata": {},
|
| 109 |
+
"output_type": "display_data"
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"data": {
|
| 113 |
+
"text/plain": [
|
| 114 |
+
"CommitInfo(commit_url='https://huggingface.co/OpenOpenAI/ppo_iter_14/commit/f131fe145e8337eb720d51d26379a261d7cc38df', commit_message='Upload model', commit_description='', oid='f131fe145e8337eb720d51d26379a261d7cc38df', pr_url=None, pr_revision=None, pr_num=None)"
|
| 115 |
+
]
|
| 116 |
+
},
|
| 117 |
+
"execution_count": 11,
|
| 118 |
+
"metadata": {},
|
| 119 |
+
"output_type": "execute_result"
|
| 120 |
+
}
|
| 121 |
+
],
|
| 122 |
+
"source": [
|
| 123 |
+
"model.push_to_hub('OpenOpenAI/ppo_iter_14')"
|
| 124 |
+
]
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"cell_type": "code",
|
| 128 |
+
"execution_count": 21,
|
| 129 |
+
"id": "6b467741-9810-4495-a968-64bdeb8d55cd",
|
| 130 |
+
"metadata": {},
|
| 131 |
+
"outputs": [
|
| 132 |
+
{
|
| 133 |
+
"data": {
|
| 134 |
+
"text/plain": [
|
| 135 |
+
"CommitInfo(commit_url='https://huggingface.co/OpenOpenAI/ppo_iter_14/commit/3f245ca9967e3784192045bd2064da5801d6e171', commit_message='Upload config', commit_description='', oid='3f245ca9967e3784192045bd2064da5801d6e171', pr_url=None, pr_revision=None, pr_num=None)"
|
| 136 |
+
]
|
| 137 |
+
},
|
| 138 |
+
"execution_count": 21,
|
| 139 |
+
"metadata": {},
|
| 140 |
+
"output_type": "execute_result"
|
| 141 |
+
}
|
| 142 |
+
],
|
| 143 |
+
"source": [
|
| 144 |
+
"config.push_to_hub('OpenOpenAI/ppo_iter_14')"
|
| 145 |
+
]
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"cell_type": "code",
|
| 149 |
+
"execution_count": 17,
|
| 150 |
+
"id": "37bb8dbb-f2cd-46cd-bdcd-906b0ae6e74e",
|
| 151 |
+
"metadata": {},
|
| 152 |
+
"outputs": [
|
| 153 |
+
{
|
| 154 |
+
"data": {
|
| 155 |
+
"application/vnd.jupyter.widget-view+json": {
|
| 156 |
+
"model_id": "c2857b5b6b824996a40de218bbab77f2",
|
| 157 |
+
"version_major": 2,
|
| 158 |
+
"version_minor": 0
|
| 159 |
+
},
|
| 160 |
+
"text/plain": [
|
| 161 |
+
"README.md: 0%| | 0.00/5.17k [00:00<?, ?B/s]"
|
| 162 |
+
]
|
| 163 |
+
},
|
| 164 |
+
"metadata": {},
|
| 165 |
+
"output_type": "display_data"
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"data": {
|
| 169 |
+
"text/plain": [
|
| 170 |
+
"CommitInfo(commit_url='https://huggingface.co/OpenOpenAI/checkpoint-2500/commit/77f7dc75043b34bc2e8b677cf9bc9440a4b56937', commit_message='Upload tokenizer', commit_description='', oid='77f7dc75043b34bc2e8b677cf9bc9440a4b56937', pr_url=None, pr_revision=None, pr_num=None)"
|
| 171 |
+
]
|
| 172 |
+
},
|
| 173 |
+
"execution_count": 17,
|
| 174 |
+
"metadata": {},
|
| 175 |
+
"output_type": "execute_result"
|
| 176 |
+
}
|
| 177 |
+
],
|
| 178 |
+
"source": [
|
| 179 |
+
"tokenizer.push_to_hub('OpenOpenAI/checkpoint-2500')"
|
| 180 |
+
]
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"cell_type": "code",
|
| 184 |
+
"execution_count": 19,
|
| 185 |
+
"id": "62eedc73-6524-4cdb-933a-702e1812b9bb",
|
| 186 |
+
"metadata": {},
|
| 187 |
+
"outputs": [
|
| 188 |
+
{
|
| 189 |
+
"data": {
|
| 190 |
+
"text/plain": [
|
| 191 |
+
"CommitInfo(commit_url='https://huggingface.co/OpenOpenAI/checkpoint-2500/commit/ccdb68475a6b305183c27d9772fd4af0949f78b5', commit_message='Upload config', commit_description='', oid='ccdb68475a6b305183c27d9772fd4af0949f78b5', pr_url=None, pr_revision=None, pr_num=None)"
|
| 192 |
+
]
|
| 193 |
+
},
|
| 194 |
+
"execution_count": 19,
|
| 195 |
+
"metadata": {},
|
| 196 |
+
"output_type": "execute_result"
|
| 197 |
+
}
|
| 198 |
+
],
|
| 199 |
+
"source": [
|
| 200 |
+
"config.push_to_hub('OpenOpenAI/checkpoint-2500')"
|
| 201 |
+
]
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"cell_type": "code",
|
| 205 |
+
"execution_count": 18,
|
| 206 |
+
"id": "acc6a23e-c7c7-404e-a51f-e5b7a0ad0df9",
|
| 207 |
+
"metadata": {},
|
| 208 |
+
"outputs": [
|
| 209 |
+
{
|
| 210 |
+
"data": {
|
| 211 |
+
"application/vnd.jupyter.widget-view+json": {
|
| 212 |
+
"model_id": "d04b28ff3e8246dc803a95bb4f15d3c2",
|
| 213 |
+
"version_major": 2,
|
| 214 |
+
"version_minor": 0
|
| 215 |
+
},
|
| 216 |
+
"text/plain": [
|
| 217 |
+
"tokenizer_config.json: 0%| | 0.00/7.51k [00:00<?, ?B/s]"
|
| 218 |
+
]
|
| 219 |
+
},
|
| 220 |
+
"metadata": {},
|
| 221 |
+
"output_type": "display_data"
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"data": {
|
| 225 |
+
"application/vnd.jupyter.widget-view+json": {
|
| 226 |
+
"model_id": "29dd2c2cf11140d5b967ecfc19fe2c68",
|
| 227 |
+
"version_major": 2,
|
| 228 |
+
"version_minor": 0
|
| 229 |
+
},
|
| 230 |
+
"text/plain": [
|
| 231 |
+
"vocab.json: 0%| | 0.00/798k [00:00<?, ?B/s]"
|
| 232 |
+
]
|
| 233 |
+
},
|
| 234 |
+
"metadata": {},
|
| 235 |
+
"output_type": "display_data"
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"data": {
|
| 239 |
+
"application/vnd.jupyter.widget-view+json": {
|
| 240 |
+
"model_id": "14a2f9cd8d0e4c7faef69ebe828fb142",
|
| 241 |
+
"version_major": 2,
|
| 242 |
+
"version_minor": 0
|
| 243 |
+
},
|
| 244 |
+
"text/plain": [
|
| 245 |
+
"merges.txt: 0%| | 0.00/456k [00:00<?, ?B/s]"
|
| 246 |
+
]
|
| 247 |
+
},
|
| 248 |
+
"metadata": {},
|
| 249 |
+
"output_type": "display_data"
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"data": {
|
| 253 |
+
"application/vnd.jupyter.widget-view+json": {
|
| 254 |
+
"model_id": "fd232cd0227c48fa8923669b8afa40b8",
|
| 255 |
+
"version_major": 2,
|
| 256 |
+
"version_minor": 0
|
| 257 |
+
},
|
| 258 |
+
"text/plain": [
|
| 259 |
+
"tokenizer.json: 0%| | 0.00/2.12M [00:00<?, ?B/s]"
|
| 260 |
+
]
|
| 261 |
+
},
|
| 262 |
+
"metadata": {},
|
| 263 |
+
"output_type": "display_data"
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"data": {
|
| 267 |
+
"application/vnd.jupyter.widget-view+json": {
|
| 268 |
+
"model_id": "62b052078fca48e2ae4a3b928671c3ff",
|
| 269 |
+
"version_major": 2,
|
| 270 |
+
"version_minor": 0
|
| 271 |
+
},
|
| 272 |
+
"text/plain": [
|
| 273 |
+
"added_tokens.json: 0%| | 0.00/1.08k [00:00<?, ?B/s]"
|
| 274 |
+
]
|
| 275 |
+
},
|
| 276 |
+
"metadata": {},
|
| 277 |
+
"output_type": "display_data"
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"data": {
|
| 281 |
+
"application/vnd.jupyter.widget-view+json": {
|
| 282 |
+
"model_id": "e49797476ec14ef99a1161a673030aa4",
|
| 283 |
+
"version_major": 2,
|
| 284 |
+
"version_minor": 0
|
| 285 |
+
},
|
| 286 |
+
"text/plain": [
|
| 287 |
+
"special_tokens_map.json: 0%| | 0.00/587 [00:00<?, ?B/s]"
|
| 288 |
+
]
|
| 289 |
+
},
|
| 290 |
+
"metadata": {},
|
| 291 |
+
"output_type": "display_data"
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"data": {
|
| 295 |
+
"application/vnd.jupyter.widget-view+json": {
|
| 296 |
+
"model_id": "1a52317f238f496892f43e940b0f88f5",
|
| 297 |
+
"version_major": 2,
|
| 298 |
+
"version_minor": 0
|
| 299 |
+
},
|
| 300 |
+
"text/plain": [
|
| 301 |
+
"model.safetensors.index.json: 0%| | 0.00/24.7k [00:00<?, ?B/s]"
|
| 302 |
+
]
|
| 303 |
+
},
|
| 304 |
+
"metadata": {},
|
| 305 |
+
"output_type": "display_data"
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"data": {
|
| 309 |
+
"application/vnd.jupyter.widget-view+json": {
|
| 310 |
+
"model_id": "756caaf635bf477e815b198d3c1a4bae",
|
| 311 |
+
"version_major": 2,
|
| 312 |
+
"version_minor": 0
|
| 313 |
+
},
|
| 314 |
+
"text/plain": [
|
| 315 |
+
"Downloading shards: 0%| | 0/2 [00:00<?, ?it/s]"
|
| 316 |
+
]
|
| 317 |
+
},
|
| 318 |
+
"metadata": {},
|
| 319 |
+
"output_type": "display_data"
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"data": {
|
| 323 |
+
"application/vnd.jupyter.widget-view+json": {
|
| 324 |
+
"model_id": "20ee3df9a2794587acfa73cadb03a39f",
|
| 325 |
+
"version_major": 2,
|
| 326 |
+
"version_minor": 0
|
| 327 |
+
},
|
| 328 |
+
"text/plain": [
|
| 329 |
+
"model-00001-of-00002.safetensors: 0%| | 0.00/4.98G [00:00<?, ?B/s]"
|
| 330 |
+
]
|
| 331 |
+
},
|
| 332 |
+
"metadata": {},
|
| 333 |
+
"output_type": "display_data"
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"ename": "KeyboardInterrupt",
|
| 337 |
+
"evalue": "",
|
| 338 |
+
"output_type": "error",
|
| 339 |
+
"traceback": [
|
| 340 |
+
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
|
| 341 |
+
"\u001b[0;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)",
|
| 342 |
+
"Cell \u001b[0;32mIn[18], line 5\u001b[0m\n\u001b[1;32m 2\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtransformers\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m AutoTokenizer, AutoModel\n\u001b[1;32m 4\u001b[0m tokenizer \u001b[38;5;241m=\u001b[39m AutoTokenizer\u001b[38;5;241m.\u001b[39mfrom_pretrained(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mOpenOpenAI/checkpoint-2500\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m----> 5\u001b[0m model \u001b[38;5;241m=\u001b[39m \u001b[43mAutoModel\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfrom_pretrained\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mOpenOpenAI/checkpoint-2500\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\n",
|
| 343 |
+
"File \u001b[0;32m/usr/local/lib/python3.10/dist-packages/transformers/models/auto/auto_factory.py:564\u001b[0m, in \u001b[0;36m_BaseAutoModelClass.from_pretrained\u001b[0;34m(cls, pretrained_model_name_or_path, *model_args, **kwargs)\u001b[0m\n\u001b[1;32m 562\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m \u001b[38;5;28mtype\u001b[39m(config) \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mcls\u001b[39m\u001b[38;5;241m.\u001b[39m_model_mapping\u001b[38;5;241m.\u001b[39mkeys():\n\u001b[1;32m 563\u001b[0m model_class \u001b[38;5;241m=\u001b[39m _get_model_class(config, \u001b[38;5;28mcls\u001b[39m\u001b[38;5;241m.\u001b[39m_model_mapping)\n\u001b[0;32m--> 564\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mmodel_class\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfrom_pretrained\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 565\u001b[0m \u001b[43m \u001b[49m\u001b[43mpretrained_model_name_or_path\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mmodel_args\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mconfig\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mconfig\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mhub_kwargs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\n\u001b[1;32m 566\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 567\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\n\u001b[1;32m 568\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mUnrecognized configuration class \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mconfig\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__class__\u001b[39m\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m for this kind of AutoModel: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;28mcls\u001b[39m\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__name__\u001b[39m\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m.\u001b[39m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 569\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mModel type should be one of \u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m, \u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;241m.\u001b[39mjoin(c\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__name__\u001b[39m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mfor\u001b[39;00m\u001b[38;5;250m \u001b[39mc\u001b[38;5;250m \u001b[39m\u001b[38;5;129;01min\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28mcls\u001b[39m\u001b[38;5;241m.\u001b[39m_model_mapping\u001b[38;5;241m.\u001b[39mkeys())\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m.\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 570\u001b[0m )\n",
|
| 344 |
+
"File \u001b[0;32m/usr/local/lib/python3.10/dist-packages/transformers/modeling_utils.py:3658\u001b[0m, in \u001b[0;36mPreTrainedModel.from_pretrained\u001b[0;34m(cls, pretrained_model_name_or_path, config, cache_dir, ignore_mismatched_sizes, force_download, local_files_only, token, revision, use_safetensors, *model_args, **kwargs)\u001b[0m\n\u001b[1;32m 3655\u001b[0m \u001b[38;5;66;03m# We'll need to download and cache each checkpoint shard if the checkpoint is sharded.\u001b[39;00m\n\u001b[1;32m 3656\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m is_sharded:\n\u001b[1;32m 3657\u001b[0m \u001b[38;5;66;03m# resolved_archive_file becomes a list of files that point to the different checkpoint shards in this case.\u001b[39;00m\n\u001b[0;32m-> 3658\u001b[0m resolved_archive_file, sharded_metadata \u001b[38;5;241m=\u001b[39m \u001b[43mget_checkpoint_shard_files\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 3659\u001b[0m \u001b[43m \u001b[49m\u001b[43mpretrained_model_name_or_path\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 3660\u001b[0m \u001b[43m \u001b[49m\u001b[43mresolved_archive_file\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 3661\u001b[0m \u001b[43m \u001b[49m\u001b[43mcache_dir\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcache_dir\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 3662\u001b[0m \u001b[43m \u001b[49m\u001b[43mforce_download\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mforce_download\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 3663\u001b[0m \u001b[43m \u001b[49m\u001b[43mproxies\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mproxies\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 3664\u001b[0m \u001b[43m \u001b[49m\u001b[43mresume_download\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mresume_download\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 3665\u001b[0m \u001b[43m \u001b[49m\u001b[43mlocal_files_only\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mlocal_files_only\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 3666\u001b[0m \u001b[43m \u001b[49m\u001b[43mtoken\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtoken\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 3667\u001b[0m \u001b[43m \u001b[49m\u001b[43muser_agent\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43muser_agent\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 3668\u001b[0m \u001b[43m \u001b[49m\u001b[43mrevision\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrevision\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 3669\u001b[0m \u001b[43m \u001b[49m\u001b[43msubfolder\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43msubfolder\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 3670\u001b[0m \u001b[43m \u001b[49m\u001b[43m_commit_hash\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcommit_hash\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 3671\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 3673\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m (\n\u001b[1;32m 3674\u001b[0m is_safetensors_available()\n\u001b[1;32m 3675\u001b[0m \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(resolved_archive_file, \u001b[38;5;28mstr\u001b[39m)\n\u001b[1;32m 3676\u001b[0m \u001b[38;5;129;01mand\u001b[39;00m resolved_archive_file\u001b[38;5;241m.\u001b[39mendswith(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m.safetensors\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m 3677\u001b[0m ):\n\u001b[1;32m 3678\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m safe_open(resolved_archive_file, framework\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mpt\u001b[39m\u001b[38;5;124m\"\u001b[39m) \u001b[38;5;28;01mas\u001b[39;00m f:\n",
|
| 345 |
+
"File \u001b[0;32m/usr/local/lib/python3.10/dist-packages/transformers/utils/hub.py:1079\u001b[0m, in \u001b[0;36mget_checkpoint_shard_files\u001b[0;34m(pretrained_model_name_or_path, index_filename, cache_dir, force_download, proxies, resume_download, local_files_only, token, user_agent, revision, subfolder, _commit_hash, **deprecated_kwargs)\u001b[0m\n\u001b[1;32m 1076\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m shard_filename \u001b[38;5;129;01min\u001b[39;00m tqdm(shard_filenames, desc\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mDownloading shards\u001b[39m\u001b[38;5;124m\"\u001b[39m, disable\u001b[38;5;241m=\u001b[39m\u001b[38;5;129;01mnot\u001b[39;00m show_progress_bar):\n\u001b[1;32m 1077\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m 1078\u001b[0m \u001b[38;5;66;03m# Load from URL\u001b[39;00m\n\u001b[0;32m-> 1079\u001b[0m cached_filename \u001b[38;5;241m=\u001b[39m \u001b[43mcached_file\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 1080\u001b[0m \u001b[43m \u001b[49m\u001b[43mpretrained_model_name_or_path\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1081\u001b[0m \u001b[43m \u001b[49m\u001b[43mshard_filename\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1082\u001b[0m \u001b[43m \u001b[49m\u001b[43mcache_dir\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcache_dir\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1083\u001b[0m \u001b[43m \u001b[49m\u001b[43mforce_download\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mforce_download\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1084\u001b[0m \u001b[43m \u001b[49m\u001b[43mproxies\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mproxies\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1085\u001b[0m \u001b[43m \u001b[49m\u001b[43mresume_download\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mresume_download\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1086\u001b[0m \u001b[43m \u001b[49m\u001b[43mlocal_files_only\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mlocal_files_only\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1087\u001b[0m \u001b[43m \u001b[49m\u001b[43mtoken\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtoken\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1088\u001b[0m \u001b[43m \u001b[49m\u001b[43muser_agent\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43muser_agent\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1089\u001b[0m \u001b[43m \u001b[49m\u001b[43mrevision\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrevision\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1090\u001b[0m \u001b[43m \u001b[49m\u001b[43msubfolder\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43msubfolder\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1091\u001b[0m \u001b[43m \u001b[49m\u001b[43m_commit_hash\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m_commit_hash\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1092\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1093\u001b[0m \u001b[38;5;66;03m# We have already dealt with RepositoryNotFoundError and RevisionNotFoundError when getting the index, so\u001b[39;00m\n\u001b[1;32m 1094\u001b[0m \u001b[38;5;66;03m# we don't have to catch them here.\u001b[39;00m\n\u001b[1;32m 1095\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m EntryNotFoundError:\n",
|
| 346 |
+
"File \u001b[0;32m/usr/local/lib/python3.10/dist-packages/transformers/utils/hub.py:402\u001b[0m, in \u001b[0;36mcached_file\u001b[0;34m(path_or_repo_id, filename, cache_dir, force_download, resume_download, proxies, token, revision, local_files_only, subfolder, repo_type, user_agent, _raise_exceptions_for_gated_repo, _raise_exceptions_for_missing_entries, _raise_exceptions_for_connection_errors, _commit_hash, **deprecated_kwargs)\u001b[0m\n\u001b[1;32m 399\u001b[0m user_agent \u001b[38;5;241m=\u001b[39m http_user_agent(user_agent)\n\u001b[1;32m 400\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m 401\u001b[0m \u001b[38;5;66;03m# Load from URL or cache if already cached\u001b[39;00m\n\u001b[0;32m--> 402\u001b[0m resolved_file \u001b[38;5;241m=\u001b[39m \u001b[43mhf_hub_download\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 403\u001b[0m \u001b[43m \u001b[49m\u001b[43mpath_or_repo_id\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 404\u001b[0m \u001b[43m \u001b[49m\u001b[43mfilename\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 405\u001b[0m \u001b[43m \u001b[49m\u001b[43msubfolder\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mif\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43mlen\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43msubfolder\u001b[49m\u001b[43m)\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m==\u001b[39;49m\u001b[43m \u001b[49m\u001b[38;5;241;43m0\u001b[39;49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01melse\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43msubfolder\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 406\u001b[0m \u001b[43m \u001b[49m\u001b[43mrepo_type\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrepo_type\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 407\u001b[0m \u001b[43m \u001b[49m\u001b[43mrevision\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrevision\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 408\u001b[0m \u001b[43m \u001b[49m\u001b[43mcache_dir\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcache_dir\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 409\u001b[0m \u001b[43m \u001b[49m\u001b[43muser_agent\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43muser_agent\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 410\u001b[0m \u001b[43m \u001b[49m\u001b[43mforce_download\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mforce_download\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 411\u001b[0m \u001b[43m \u001b[49m\u001b[43mproxies\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mproxies\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 412\u001b[0m \u001b[43m \u001b[49m\u001b[43mresume_download\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mresume_download\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 413\u001b[0m \u001b[43m \u001b[49m\u001b[43mtoken\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtoken\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 414\u001b[0m \u001b[43m \u001b[49m\u001b[43mlocal_files_only\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mlocal_files_only\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 415\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 416\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m GatedRepoError \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m 417\u001b[0m resolved_file \u001b[38;5;241m=\u001b[39m _get_cache_file_to_return(path_or_repo_id, full_filename, cache_dir, revision)\n",
|
| 347 |
+
"File \u001b[0;32m/usr/local/lib/python3.10/dist-packages/huggingface_hub/utils/_deprecation.py:101\u001b[0m, in \u001b[0;36m_deprecate_arguments.<locals>._inner_deprecate_positional_args.<locals>.inner_f\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 99\u001b[0m message \u001b[38;5;241m+\u001b[39m\u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;241m+\u001b[39m custom_message\n\u001b[1;32m 100\u001b[0m warnings\u001b[38;5;241m.\u001b[39mwarn(message, \u001b[38;5;167;01mFutureWarning\u001b[39;00m)\n\u001b[0;32m--> 101\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mf\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
|
| 348 |
+
"File \u001b[0;32m/usr/local/lib/python3.10/dist-packages/huggingface_hub/utils/_validators.py:114\u001b[0m, in \u001b[0;36mvalidate_hf_hub_args.<locals>._inner_fn\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 111\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m check_use_auth_token:\n\u001b[1;32m 112\u001b[0m kwargs \u001b[38;5;241m=\u001b[39m smoothly_deprecate_use_auth_token(fn_name\u001b[38;5;241m=\u001b[39mfn\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__name__\u001b[39m, has_token\u001b[38;5;241m=\u001b[39mhas_token, kwargs\u001b[38;5;241m=\u001b[39mkwargs)\n\u001b[0;32m--> 114\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfn\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
|
| 349 |
+
"File \u001b[0;32m/usr/local/lib/python3.10/dist-packages/huggingface_hub/file_download.py:1240\u001b[0m, in \u001b[0;36mhf_hub_download\u001b[0;34m(repo_id, filename, subfolder, repo_type, revision, library_name, library_version, cache_dir, local_dir, user_agent, force_download, proxies, etag_timeout, token, local_files_only, headers, endpoint, legacy_cache_layout, resume_download, force_filename, local_dir_use_symlinks)\u001b[0m\n\u001b[1;32m 1220\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m _hf_hub_download_to_local_dir(\n\u001b[1;32m 1221\u001b[0m \u001b[38;5;66;03m# Destination\u001b[39;00m\n\u001b[1;32m 1222\u001b[0m local_dir\u001b[38;5;241m=\u001b[39mlocal_dir,\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 1237\u001b[0m local_files_only\u001b[38;5;241m=\u001b[39mlocal_files_only,\n\u001b[1;32m 1238\u001b[0m )\n\u001b[1;32m 1239\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 1240\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43m_hf_hub_download_to_cache_dir\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 1241\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;66;43;03m# Destination\u001b[39;49;00m\n\u001b[1;32m 1242\u001b[0m \u001b[43m \u001b[49m\u001b[43mcache_dir\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcache_dir\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1243\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;66;43;03m# File info\u001b[39;49;00m\n\u001b[1;32m 1244\u001b[0m \u001b[43m \u001b[49m\u001b[43mrepo_id\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrepo_id\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1245\u001b[0m \u001b[43m \u001b[49m\u001b[43mfilename\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mfilename\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1246\u001b[0m \u001b[43m \u001b[49m\u001b[43mrepo_type\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrepo_type\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1247\u001b[0m \u001b[43m \u001b[49m\u001b[43mrevision\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrevision\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1248\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;66;43;03m# HTTP info\u001b[39;49;00m\n\u001b[1;32m 1249\u001b[0m \u001b[43m \u001b[49m\u001b[43mendpoint\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mendpoint\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1250\u001b[0m \u001b[43m \u001b[49m\u001b[43metag_timeout\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43metag_timeout\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1251\u001b[0m \u001b[43m \u001b[49m\u001b[43mheaders\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mheaders\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1252\u001b[0m \u001b[43m \u001b[49m\u001b[43mproxies\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mproxies\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1253\u001b[0m \u001b[43m \u001b[49m\u001b[43mtoken\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtoken\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1254\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;66;43;03m# Additional options\u001b[39;49;00m\n\u001b[1;32m 1255\u001b[0m \u001b[43m \u001b[49m\u001b[43mlocal_files_only\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mlocal_files_only\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1256\u001b[0m \u001b[43m \u001b[49m\u001b[43mforce_download\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mforce_download\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1257\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n",
|
| 350 |
+
"File \u001b[0;32m/usr/local/lib/python3.10/dist-packages/huggingface_hub/file_download.py:1389\u001b[0m, in \u001b[0;36m_hf_hub_download_to_cache_dir\u001b[0;34m(cache_dir, repo_id, filename, repo_type, revision, endpoint, etag_timeout, headers, proxies, token, local_files_only, force_download)\u001b[0m\n\u001b[1;32m 1387\u001b[0m Path(lock_path)\u001b[38;5;241m.\u001b[39mparent\u001b[38;5;241m.\u001b[39mmkdir(parents\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m, exist_ok\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m)\n\u001b[1;32m 1388\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m WeakFileLock(lock_path):\n\u001b[0;32m-> 1389\u001b[0m \u001b[43m_download_to_tmp_and_move\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 1390\u001b[0m \u001b[43m \u001b[49m\u001b[43mincomplete_path\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mPath\u001b[49m\u001b[43m(\u001b[49m\u001b[43mblob_path\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m+\u001b[39;49m\u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43m.incomplete\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1391\u001b[0m \u001b[43m \u001b[49m\u001b[43mdestination_path\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mPath\u001b[49m\u001b[43m(\u001b[49m\u001b[43mblob_path\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1392\u001b[0m \u001b[43m \u001b[49m\u001b[43murl_to_download\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43murl_to_download\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1393\u001b[0m \u001b[43m \u001b[49m\u001b[43mproxies\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mproxies\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1394\u001b[0m \u001b[43m \u001b[49m\u001b[43mheaders\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mheaders\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1395\u001b[0m \u001b[43m \u001b[49m\u001b[43mexpected_size\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mexpected_size\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1396\u001b[0m \u001b[43m \u001b[49m\u001b[43mfilename\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mfilename\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1397\u001b[0m \u001b[43m \u001b[49m\u001b[43mforce_download\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mforce_download\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1398\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1399\u001b[0m _create_symlink(blob_path, pointer_path, new_blob\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m)\n\u001b[1;32m 1401\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m pointer_path\n",
|
| 351 |
+
"File \u001b[0;32m/usr/local/lib/python3.10/dist-packages/huggingface_hub/file_download.py:1915\u001b[0m, in \u001b[0;36m_download_to_tmp_and_move\u001b[0;34m(incomplete_path, destination_path, url_to_download, proxies, headers, expected_size, filename, force_download)\u001b[0m\n\u001b[1;32m 1912\u001b[0m _check_disk_space(expected_size, incomplete_path\u001b[38;5;241m.\u001b[39mparent)\n\u001b[1;32m 1913\u001b[0m _check_disk_space(expected_size, destination_path\u001b[38;5;241m.\u001b[39mparent)\n\u001b[0;32m-> 1915\u001b[0m \u001b[43mhttp_get\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 1916\u001b[0m \u001b[43m \u001b[49m\u001b[43murl_to_download\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1917\u001b[0m \u001b[43m \u001b[49m\u001b[43mf\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1918\u001b[0m \u001b[43m \u001b[49m\u001b[43mproxies\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mproxies\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1919\u001b[0m \u001b[43m \u001b[49m\u001b[43mresume_size\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mresume_size\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1920\u001b[0m \u001b[43m \u001b[49m\u001b[43mheaders\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mheaders\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1921\u001b[0m \u001b[43m \u001b[49m\u001b[43mexpected_size\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mexpected_size\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1922\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1924\u001b[0m logger\u001b[38;5;241m.\u001b[39minfo(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mDownload complete. Moving file to \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mdestination_path\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m 1925\u001b[0m _chmod_and_move(incomplete_path, destination_path)\n",
|
| 352 |
+
"File \u001b[0;32m/usr/local/lib/python3.10/dist-packages/huggingface_hub/file_download.py:549\u001b[0m, in \u001b[0;36mhttp_get\u001b[0;34m(url, temp_file, proxies, resume_size, headers, expected_size, displayed_filename, _nb_retries, _tqdm_bar)\u001b[0m\n\u001b[1;32m 547\u001b[0m new_resume_size \u001b[38;5;241m=\u001b[39m resume_size\n\u001b[1;32m 548\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 549\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m chunk \u001b[38;5;129;01min\u001b[39;00m r\u001b[38;5;241m.\u001b[39miter_content(chunk_size\u001b[38;5;241m=\u001b[39mDOWNLOAD_CHUNK_SIZE):\n\u001b[1;32m 550\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m chunk: \u001b[38;5;66;03m# filter out keep-alive new chunks\u001b[39;00m\n\u001b[1;32m 551\u001b[0m progress\u001b[38;5;241m.\u001b[39mupdate(\u001b[38;5;28mlen\u001b[39m(chunk))\n",
|
| 353 |
+
"File \u001b[0;32m/usr/local/lib/python3.10/dist-packages/requests/models.py:820\u001b[0m, in \u001b[0;36mResponse.iter_content.<locals>.generate\u001b[0;34m()\u001b[0m\n\u001b[1;32m 818\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mhasattr\u001b[39m(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mraw, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mstream\u001b[39m\u001b[38;5;124m\"\u001b[39m):\n\u001b[1;32m 819\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 820\u001b[0m \u001b[38;5;28;01myield from\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mraw\u001b[38;5;241m.\u001b[39mstream(chunk_size, decode_content\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m)\n\u001b[1;32m 821\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m ProtocolError \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m 822\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m ChunkedEncodingError(e)\n",
|
| 354 |
+
"File \u001b[0;32m/usr/local/lib/python3.10/dist-packages/urllib3/response.py:628\u001b[0m, in \u001b[0;36mHTTPResponse.stream\u001b[0;34m(self, amt, decode_content)\u001b[0m\n\u001b[1;32m 626\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 627\u001b[0m \u001b[38;5;28;01mwhile\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m is_fp_closed(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_fp):\n\u001b[0;32m--> 628\u001b[0m data \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mread\u001b[49m\u001b[43m(\u001b[49m\u001b[43mamt\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mamt\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mdecode_content\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mdecode_content\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 630\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m data:\n\u001b[1;32m 631\u001b[0m \u001b[38;5;28;01myield\u001b[39;00m data\n",
|
| 355 |
+
"File \u001b[0;32m/usr/local/lib/python3.10/dist-packages/urllib3/response.py:567\u001b[0m, in \u001b[0;36mHTTPResponse.read\u001b[0;34m(self, amt, decode_content, cache_content)\u001b[0m\n\u001b[1;32m 564\u001b[0m fp_closed \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mgetattr\u001b[39m(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_fp, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mclosed\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;28;01mFalse\u001b[39;00m)\n\u001b[1;32m 566\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_error_catcher():\n\u001b[0;32m--> 567\u001b[0m data \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_fp_read\u001b[49m\u001b[43m(\u001b[49m\u001b[43mamt\u001b[49m\u001b[43m)\u001b[49m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m fp_closed \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;124mb\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 568\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m amt \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m 569\u001b[0m flush_decoder \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mTrue\u001b[39;00m\n",
|
| 356 |
+
"File \u001b[0;32m/usr/local/lib/python3.10/dist-packages/urllib3/response.py:533\u001b[0m, in \u001b[0;36mHTTPResponse._fp_read\u001b[0;34m(self, amt)\u001b[0m\n\u001b[1;32m 530\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m buffer\u001b[38;5;241m.\u001b[39mgetvalue()\n\u001b[1;32m 531\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 532\u001b[0m \u001b[38;5;66;03m# StringIO doesn't like amt=None\u001b[39;00m\n\u001b[0;32m--> 533\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_fp\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mread\u001b[49m\u001b[43m(\u001b[49m\u001b[43mamt\u001b[49m\u001b[43m)\u001b[49m \u001b[38;5;28;01mif\u001b[39;00m amt \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_fp\u001b[38;5;241m.\u001b[39mread()\n",
|
| 357 |
+
"File \u001b[0;32m/usr/lib/python3.10/http/client.py:466\u001b[0m, in \u001b[0;36mHTTPResponse.read\u001b[0;34m(self, amt)\u001b[0m\n\u001b[1;32m 463\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mlength \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;129;01mand\u001b[39;00m amt \u001b[38;5;241m>\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mlength:\n\u001b[1;32m 464\u001b[0m \u001b[38;5;66;03m# clip the read to the \"end of response\"\u001b[39;00m\n\u001b[1;32m 465\u001b[0m amt \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mlength\n\u001b[0;32m--> 466\u001b[0m s \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfp\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mread\u001b[49m\u001b[43m(\u001b[49m\u001b[43mamt\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 467\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m s \u001b[38;5;129;01mand\u001b[39;00m amt:\n\u001b[1;32m 468\u001b[0m \u001b[38;5;66;03m# Ideally, we would raise IncompleteRead if the content-length\u001b[39;00m\n\u001b[1;32m 469\u001b[0m \u001b[38;5;66;03m# wasn't satisfied, but it might break compatibility.\u001b[39;00m\n\u001b[1;32m 470\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_close_conn()\n",
|
| 358 |
+
"File \u001b[0;32m/usr/lib/python3.10/socket.py:705\u001b[0m, in \u001b[0;36mSocketIO.readinto\u001b[0;34m(self, b)\u001b[0m\n\u001b[1;32m 703\u001b[0m \u001b[38;5;28;01mwhile\u001b[39;00m \u001b[38;5;28;01mTrue\u001b[39;00m:\n\u001b[1;32m 704\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 705\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_sock\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mrecv_into\u001b[49m\u001b[43m(\u001b[49m\u001b[43mb\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 706\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m timeout:\n\u001b[1;32m 707\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_timeout_occurred \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mTrue\u001b[39;00m\n",
|
| 359 |
+
"File \u001b[0;32m/usr/lib/python3.10/ssl.py:1274\u001b[0m, in \u001b[0;36mSSLSocket.recv_into\u001b[0;34m(self, buffer, nbytes, flags)\u001b[0m\n\u001b[1;32m 1270\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m flags \u001b[38;5;241m!=\u001b[39m \u001b[38;5;241m0\u001b[39m:\n\u001b[1;32m 1271\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\n\u001b[1;32m 1272\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mnon-zero flags not allowed in calls to recv_into() on \u001b[39m\u001b[38;5;132;01m%s\u001b[39;00m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;241m%\u001b[39m\n\u001b[1;32m 1273\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__class__\u001b[39m)\n\u001b[0;32m-> 1274\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mread\u001b[49m\u001b[43m(\u001b[49m\u001b[43mnbytes\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mbuffer\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1275\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 1276\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28msuper\u001b[39m()\u001b[38;5;241m.\u001b[39mrecv_into(buffer, nbytes, flags)\n",
|
| 360 |
+
"File \u001b[0;32m/usr/lib/python3.10/ssl.py:1130\u001b[0m, in \u001b[0;36mSSLSocket.read\u001b[0;34m(self, len, buffer)\u001b[0m\n\u001b[1;32m 1128\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m 1129\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m buffer \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[0;32m-> 1130\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_sslobj\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mread\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mlen\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mbuffer\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1131\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 1132\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_sslobj\u001b[38;5;241m.\u001b[39mread(\u001b[38;5;28mlen\u001b[39m)\n",
|
| 361 |
+
"\u001b[0;31mKeyboardInterrupt\u001b[0m: "
|
| 362 |
+
]
|
| 363 |
+
}
|
| 364 |
+
],
|
| 365 |
+
"source": [
|
| 366 |
+
"# Load model directly\n",
|
| 367 |
+
"from transformers import AutoTokenizer, AutoModel\n",
|
| 368 |
+
"\n",
|
| 369 |
+
"tokenizer = AutoTokenizer.from_pretrained(\"OpenOpenAI/checkpoint-2500\")\n",
|
| 370 |
+
"model = AutoModel.from_pretrained(\"OpenOpenAI/checkpoint-2500\")"
|
| 371 |
+
]
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"cell_type": "code",
|
| 375 |
+
"execution_count": null,
|
| 376 |
+
"id": "d3443f20-cd0e-4fa0-97ab-a69f73c72be6",
|
| 377 |
+
"metadata": {},
|
| 378 |
+
"outputs": [],
|
| 379 |
+
"source": []
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"cell_type": "code",
|
| 383 |
+
"execution_count": null,
|
| 384 |
+
"id": "65b919ca-4d3c-49bf-a0bc-4240defb84d1",
|
| 385 |
+
"metadata": {},
|
| 386 |
+
"outputs": [],
|
| 387 |
+
"source": []
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"cell_type": "code",
|
| 391 |
+
"execution_count": 22,
|
| 392 |
+
"id": "5000a1a2-a562-403e-af50-9477a3ecbcbb",
|
| 393 |
+
"metadata": {},
|
| 394 |
+
"outputs": [
|
| 395 |
+
{
|
| 396 |
+
"data": {
|
| 397 |
+
"application/vnd.jupyter.widget-view+json": {
|
| 398 |
+
"model_id": "ce2c8a458e2f48209383c557f58f1e5d",
|
| 399 |
+
"version_major": 2,
|
| 400 |
+
"version_minor": 0
|
| 401 |
+
},
|
| 402 |
+
"text/plain": [
|
| 403 |
+
"config.json: 0%| | 0.00/743 [00:00<?, ?B/s]"
|
| 404 |
+
]
|
| 405 |
+
},
|
| 406 |
+
"metadata": {},
|
| 407 |
+
"output_type": "display_data"
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"data": {
|
| 411 |
+
"application/vnd.jupyter.widget-view+json": {
|
| 412 |
+
"model_id": "eae84f82c9304d9f8af556958830f436",
|
| 413 |
+
"version_major": 2,
|
| 414 |
+
"version_minor": 0
|
| 415 |
+
},
|
| 416 |
+
"text/plain": [
|
| 417 |
+
"Downloading shards: 0%| | 0/2 [00:00<?, ?it/s]"
|
| 418 |
+
]
|
| 419 |
+
},
|
| 420 |
+
"metadata": {},
|
| 421 |
+
"output_type": "display_data"
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"data": {
|
| 425 |
+
"application/vnd.jupyter.widget-view+json": {
|
| 426 |
+
"model_id": "7b95d784fc494882852373c34cbd4019",
|
| 427 |
+
"version_major": 2,
|
| 428 |
+
"version_minor": 0
|
| 429 |
+
},
|
| 430 |
+
"text/plain": [
|
| 431 |
+
"model-00001-of-00002.safetensors: 5%|4 | 241M/4.98G [00:00<?, ?B/s]"
|
| 432 |
+
]
|
| 433 |
+
},
|
| 434 |
+
"metadata": {},
|
| 435 |
+
"output_type": "display_data"
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"ename": "KeyboardInterrupt",
|
| 439 |
+
"evalue": "",
|
| 440 |
+
"output_type": "error",
|
| 441 |
+
"traceback": [
|
| 442 |
+
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
|
| 443 |
+
"\u001b[0;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)",
|
| 444 |
+
"Cell \u001b[0;32mIn[22], line 5\u001b[0m\n\u001b[1;32m 2\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtransformers\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m AutoTokenizer, AutoModel\n\u001b[1;32m 4\u001b[0m tokenizer \u001b[38;5;241m=\u001b[39m AutoTokenizer\u001b[38;5;241m.\u001b[39mfrom_pretrained(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mOpenOpenAI/checkpoint-2500\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m----> 5\u001b[0m model \u001b[38;5;241m=\u001b[39m \u001b[43mAutoModel\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfrom_pretrained\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mOpenOpenAI/checkpoint-2500\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\n",
|
| 445 |
+
"File \u001b[0;32m/usr/local/lib/python3.10/dist-packages/transformers/models/auto/auto_factory.py:564\u001b[0m, in \u001b[0;36m_BaseAutoModelClass.from_pretrained\u001b[0;34m(cls, pretrained_model_name_or_path, *model_args, **kwargs)\u001b[0m\n\u001b[1;32m 562\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m \u001b[38;5;28mtype\u001b[39m(config) \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mcls\u001b[39m\u001b[38;5;241m.\u001b[39m_model_mapping\u001b[38;5;241m.\u001b[39mkeys():\n\u001b[1;32m 563\u001b[0m model_class \u001b[38;5;241m=\u001b[39m _get_model_class(config, \u001b[38;5;28mcls\u001b[39m\u001b[38;5;241m.\u001b[39m_model_mapping)\n\u001b[0;32m--> 564\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mmodel_class\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfrom_pretrained\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 565\u001b[0m \u001b[43m \u001b[49m\u001b[43mpretrained_model_name_or_path\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mmodel_args\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mconfig\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mconfig\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mhub_kwargs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\n\u001b[1;32m 566\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 567\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\n\u001b[1;32m 568\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mUnrecognized configuration class \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mconfig\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__class__\u001b[39m\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m for this kind of AutoModel: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;28mcls\u001b[39m\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__name__\u001b[39m\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m.\u001b[39m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 569\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mModel type should be one of \u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m, \u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;241m.\u001b[39mjoin(c\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__name__\u001b[39m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mfor\u001b[39;00m\u001b[38;5;250m \u001b[39mc\u001b[38;5;250m \u001b[39m\u001b[38;5;129;01min\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28mcls\u001b[39m\u001b[38;5;241m.\u001b[39m_model_mapping\u001b[38;5;241m.\u001b[39mkeys())\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m.\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 570\u001b[0m )\n",
|
| 446 |
+
"File \u001b[0;32m/usr/local/lib/python3.10/dist-packages/transformers/modeling_utils.py:3658\u001b[0m, in \u001b[0;36mPreTrainedModel.from_pretrained\u001b[0;34m(cls, pretrained_model_name_or_path, config, cache_dir, ignore_mismatched_sizes, force_download, local_files_only, token, revision, use_safetensors, *model_args, **kwargs)\u001b[0m\n\u001b[1;32m 3655\u001b[0m \u001b[38;5;66;03m# We'll need to download and cache each checkpoint shard if the checkpoint is sharded.\u001b[39;00m\n\u001b[1;32m 3656\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m is_sharded:\n\u001b[1;32m 3657\u001b[0m \u001b[38;5;66;03m# resolved_archive_file becomes a list of files that point to the different checkpoint shards in this case.\u001b[39;00m\n\u001b[0;32m-> 3658\u001b[0m resolved_archive_file, sharded_metadata \u001b[38;5;241m=\u001b[39m \u001b[43mget_checkpoint_shard_files\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 3659\u001b[0m \u001b[43m \u001b[49m\u001b[43mpretrained_model_name_or_path\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 3660\u001b[0m \u001b[43m \u001b[49m\u001b[43mresolved_archive_file\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 3661\u001b[0m \u001b[43m \u001b[49m\u001b[43mcache_dir\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcache_dir\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 3662\u001b[0m \u001b[43m \u001b[49m\u001b[43mforce_download\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mforce_download\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 3663\u001b[0m \u001b[43m \u001b[49m\u001b[43mproxies\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mproxies\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 3664\u001b[0m \u001b[43m \u001b[49m\u001b[43mresume_download\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mresume_download\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 3665\u001b[0m \u001b[43m \u001b[49m\u001b[43mlocal_files_only\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mlocal_files_only\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 3666\u001b[0m \u001b[43m \u001b[49m\u001b[43mtoken\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtoken\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 3667\u001b[0m \u001b[43m \u001b[49m\u001b[43muser_agent\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43muser_agent\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 3668\u001b[0m \u001b[43m \u001b[49m\u001b[43mrevision\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrevision\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 3669\u001b[0m \u001b[43m \u001b[49m\u001b[43msubfolder\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43msubfolder\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 3670\u001b[0m \u001b[43m \u001b[49m\u001b[43m_commit_hash\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcommit_hash\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 3671\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 3673\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m (\n\u001b[1;32m 3674\u001b[0m is_safetensors_available()\n\u001b[1;32m 3675\u001b[0m \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(resolved_archive_file, \u001b[38;5;28mstr\u001b[39m)\n\u001b[1;32m 3676\u001b[0m \u001b[38;5;129;01mand\u001b[39;00m resolved_archive_file\u001b[38;5;241m.\u001b[39mendswith(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m.safetensors\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m 3677\u001b[0m ):\n\u001b[1;32m 3678\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m safe_open(resolved_archive_file, framework\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mpt\u001b[39m\u001b[38;5;124m\"\u001b[39m) \u001b[38;5;28;01mas\u001b[39;00m f:\n",
|
| 447 |
+
"File \u001b[0;32m/usr/local/lib/python3.10/dist-packages/transformers/utils/hub.py:1079\u001b[0m, in \u001b[0;36mget_checkpoint_shard_files\u001b[0;34m(pretrained_model_name_or_path, index_filename, cache_dir, force_download, proxies, resume_download, local_files_only, token, user_agent, revision, subfolder, _commit_hash, **deprecated_kwargs)\u001b[0m\n\u001b[1;32m 1076\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m shard_filename \u001b[38;5;129;01min\u001b[39;00m tqdm(shard_filenames, desc\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mDownloading shards\u001b[39m\u001b[38;5;124m\"\u001b[39m, disable\u001b[38;5;241m=\u001b[39m\u001b[38;5;129;01mnot\u001b[39;00m show_progress_bar):\n\u001b[1;32m 1077\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m 1078\u001b[0m \u001b[38;5;66;03m# Load from URL\u001b[39;00m\n\u001b[0;32m-> 1079\u001b[0m cached_filename \u001b[38;5;241m=\u001b[39m \u001b[43mcached_file\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 1080\u001b[0m \u001b[43m \u001b[49m\u001b[43mpretrained_model_name_or_path\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1081\u001b[0m \u001b[43m \u001b[49m\u001b[43mshard_filename\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1082\u001b[0m \u001b[43m \u001b[49m\u001b[43mcache_dir\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcache_dir\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1083\u001b[0m \u001b[43m \u001b[49m\u001b[43mforce_download\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mforce_download\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1084\u001b[0m \u001b[43m \u001b[49m\u001b[43mproxies\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mproxies\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1085\u001b[0m \u001b[43m \u001b[49m\u001b[43mresume_download\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mresume_download\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1086\u001b[0m \u001b[43m \u001b[49m\u001b[43mlocal_files_only\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mlocal_files_only\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1087\u001b[0m \u001b[43m \u001b[49m\u001b[43mtoken\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtoken\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1088\u001b[0m \u001b[43m \u001b[49m\u001b[43muser_agent\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43muser_agent\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1089\u001b[0m \u001b[43m \u001b[49m\u001b[43mrevision\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrevision\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1090\u001b[0m \u001b[43m \u001b[49m\u001b[43msubfolder\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43msubfolder\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1091\u001b[0m \u001b[43m \u001b[49m\u001b[43m_commit_hash\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m_commit_hash\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1092\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1093\u001b[0m \u001b[38;5;66;03m# We have already dealt with RepositoryNotFoundError and RevisionNotFoundError when getting the index, so\u001b[39;00m\n\u001b[1;32m 1094\u001b[0m \u001b[38;5;66;03m# we don't have to catch them here.\u001b[39;00m\n\u001b[1;32m 1095\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m EntryNotFoundError:\n",
|
| 448 |
+
"File \u001b[0;32m/usr/local/lib/python3.10/dist-packages/transformers/utils/hub.py:402\u001b[0m, in \u001b[0;36mcached_file\u001b[0;34m(path_or_repo_id, filename, cache_dir, force_download, resume_download, proxies, token, revision, local_files_only, subfolder, repo_type, user_agent, _raise_exceptions_for_gated_repo, _raise_exceptions_for_missing_entries, _raise_exceptions_for_connection_errors, _commit_hash, **deprecated_kwargs)\u001b[0m\n\u001b[1;32m 399\u001b[0m user_agent \u001b[38;5;241m=\u001b[39m http_user_agent(user_agent)\n\u001b[1;32m 400\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m 401\u001b[0m \u001b[38;5;66;03m# Load from URL or cache if already cached\u001b[39;00m\n\u001b[0;32m--> 402\u001b[0m resolved_file \u001b[38;5;241m=\u001b[39m \u001b[43mhf_hub_download\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 403\u001b[0m \u001b[43m \u001b[49m\u001b[43mpath_or_repo_id\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 404\u001b[0m \u001b[43m \u001b[49m\u001b[43mfilename\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 405\u001b[0m \u001b[43m \u001b[49m\u001b[43msubfolder\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mif\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43mlen\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43msubfolder\u001b[49m\u001b[43m)\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m==\u001b[39;49m\u001b[43m \u001b[49m\u001b[38;5;241;43m0\u001b[39;49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01melse\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43msubfolder\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 406\u001b[0m \u001b[43m \u001b[49m\u001b[43mrepo_type\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrepo_type\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 407\u001b[0m \u001b[43m \u001b[49m\u001b[43mrevision\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrevision\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 408\u001b[0m \u001b[43m \u001b[49m\u001b[43mcache_dir\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcache_dir\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 409\u001b[0m \u001b[43m \u001b[49m\u001b[43muser_agent\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43muser_agent\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 410\u001b[0m \u001b[43m \u001b[49m\u001b[43mforce_download\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mforce_download\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 411\u001b[0m \u001b[43m \u001b[49m\u001b[43mproxies\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mproxies\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 412\u001b[0m \u001b[43m \u001b[49m\u001b[43mresume_download\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mresume_download\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 413\u001b[0m \u001b[43m \u001b[49m\u001b[43mtoken\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtoken\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 414\u001b[0m \u001b[43m \u001b[49m\u001b[43mlocal_files_only\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mlocal_files_only\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 415\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 416\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m GatedRepoError \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m 417\u001b[0m resolved_file \u001b[38;5;241m=\u001b[39m _get_cache_file_to_return(path_or_repo_id, full_filename, cache_dir, revision)\n",
|
| 449 |
+
"File \u001b[0;32m/usr/local/lib/python3.10/dist-packages/huggingface_hub/utils/_deprecation.py:101\u001b[0m, in \u001b[0;36m_deprecate_arguments.<locals>._inner_deprecate_positional_args.<locals>.inner_f\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 99\u001b[0m message \u001b[38;5;241m+\u001b[39m\u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;241m+\u001b[39m custom_message\n\u001b[1;32m 100\u001b[0m warnings\u001b[38;5;241m.\u001b[39mwarn(message, \u001b[38;5;167;01mFutureWarning\u001b[39;00m)\n\u001b[0;32m--> 101\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mf\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
|
| 450 |
+
"File \u001b[0;32m/usr/local/lib/python3.10/dist-packages/huggingface_hub/utils/_validators.py:114\u001b[0m, in \u001b[0;36mvalidate_hf_hub_args.<locals>._inner_fn\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 111\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m check_use_auth_token:\n\u001b[1;32m 112\u001b[0m kwargs \u001b[38;5;241m=\u001b[39m smoothly_deprecate_use_auth_token(fn_name\u001b[38;5;241m=\u001b[39mfn\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__name__\u001b[39m, has_token\u001b[38;5;241m=\u001b[39mhas_token, kwargs\u001b[38;5;241m=\u001b[39mkwargs)\n\u001b[0;32m--> 114\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfn\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
|
| 451 |
+
"File \u001b[0;32m/usr/local/lib/python3.10/dist-packages/huggingface_hub/file_download.py:1240\u001b[0m, in \u001b[0;36mhf_hub_download\u001b[0;34m(repo_id, filename, subfolder, repo_type, revision, library_name, library_version, cache_dir, local_dir, user_agent, force_download, proxies, etag_timeout, token, local_files_only, headers, endpoint, legacy_cache_layout, resume_download, force_filename, local_dir_use_symlinks)\u001b[0m\n\u001b[1;32m 1220\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m _hf_hub_download_to_local_dir(\n\u001b[1;32m 1221\u001b[0m \u001b[38;5;66;03m# Destination\u001b[39;00m\n\u001b[1;32m 1222\u001b[0m local_dir\u001b[38;5;241m=\u001b[39mlocal_dir,\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 1237\u001b[0m local_files_only\u001b[38;5;241m=\u001b[39mlocal_files_only,\n\u001b[1;32m 1238\u001b[0m )\n\u001b[1;32m 1239\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 1240\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43m_hf_hub_download_to_cache_dir\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 1241\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;66;43;03m# Destination\u001b[39;49;00m\n\u001b[1;32m 1242\u001b[0m \u001b[43m \u001b[49m\u001b[43mcache_dir\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcache_dir\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1243\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;66;43;03m# File info\u001b[39;49;00m\n\u001b[1;32m 1244\u001b[0m \u001b[43m \u001b[49m\u001b[43mrepo_id\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrepo_id\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1245\u001b[0m \u001b[43m \u001b[49m\u001b[43mfilename\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mfilename\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1246\u001b[0m \u001b[43m \u001b[49m\u001b[43mrepo_type\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrepo_type\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1247\u001b[0m \u001b[43m \u001b[49m\u001b[43mrevision\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrevision\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1248\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;66;43;03m# HTTP info\u001b[39;49;00m\n\u001b[1;32m 1249\u001b[0m \u001b[43m \u001b[49m\u001b[43mendpoint\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mendpoint\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1250\u001b[0m \u001b[43m \u001b[49m\u001b[43metag_timeout\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43metag_timeout\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1251\u001b[0m \u001b[43m \u001b[49m\u001b[43mheaders\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mheaders\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1252\u001b[0m \u001b[43m \u001b[49m\u001b[43mproxies\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mproxies\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1253\u001b[0m \u001b[43m \u001b[49m\u001b[43mtoken\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtoken\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1254\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;66;43;03m# Additional options\u001b[39;49;00m\n\u001b[1;32m 1255\u001b[0m \u001b[43m \u001b[49m\u001b[43mlocal_files_only\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mlocal_files_only\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1256\u001b[0m \u001b[43m \u001b[49m\u001b[43mforce_download\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mforce_download\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1257\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n",
|
| 452 |
+
"File \u001b[0;32m/usr/local/lib/python3.10/dist-packages/huggingface_hub/file_download.py:1389\u001b[0m, in \u001b[0;36m_hf_hub_download_to_cache_dir\u001b[0;34m(cache_dir, repo_id, filename, repo_type, revision, endpoint, etag_timeout, headers, proxies, token, local_files_only, force_download)\u001b[0m\n\u001b[1;32m 1387\u001b[0m Path(lock_path)\u001b[38;5;241m.\u001b[39mparent\u001b[38;5;241m.\u001b[39mmkdir(parents\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m, exist_ok\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m)\n\u001b[1;32m 1388\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m WeakFileLock(lock_path):\n\u001b[0;32m-> 1389\u001b[0m \u001b[43m_download_to_tmp_and_move\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 1390\u001b[0m \u001b[43m \u001b[49m\u001b[43mincomplete_path\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mPath\u001b[49m\u001b[43m(\u001b[49m\u001b[43mblob_path\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m+\u001b[39;49m\u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43m.incomplete\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1391\u001b[0m \u001b[43m \u001b[49m\u001b[43mdestination_path\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mPath\u001b[49m\u001b[43m(\u001b[49m\u001b[43mblob_path\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1392\u001b[0m \u001b[43m \u001b[49m\u001b[43murl_to_download\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43murl_to_download\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1393\u001b[0m \u001b[43m \u001b[49m\u001b[43mproxies\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mproxies\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1394\u001b[0m \u001b[43m \u001b[49m\u001b[43mheaders\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mheaders\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1395\u001b[0m \u001b[43m \u001b[49m\u001b[43mexpected_size\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mexpected_size\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1396\u001b[0m \u001b[43m \u001b[49m\u001b[43mfilename\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mfilename\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1397\u001b[0m \u001b[43m \u001b[49m\u001b[43mforce_download\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mforce_download\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1398\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1399\u001b[0m _create_symlink(blob_path, pointer_path, new_blob\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m)\n\u001b[1;32m 1401\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m pointer_path\n",
|
| 453 |
+
"File \u001b[0;32m/usr/local/lib/python3.10/dist-packages/huggingface_hub/file_download.py:1915\u001b[0m, in \u001b[0;36m_download_to_tmp_and_move\u001b[0;34m(incomplete_path, destination_path, url_to_download, proxies, headers, expected_size, filename, force_download)\u001b[0m\n\u001b[1;32m 1912\u001b[0m _check_disk_space(expected_size, incomplete_path\u001b[38;5;241m.\u001b[39mparent)\n\u001b[1;32m 1913\u001b[0m _check_disk_space(expected_size, destination_path\u001b[38;5;241m.\u001b[39mparent)\n\u001b[0;32m-> 1915\u001b[0m \u001b[43mhttp_get\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 1916\u001b[0m \u001b[43m \u001b[49m\u001b[43murl_to_download\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1917\u001b[0m \u001b[43m \u001b[49m\u001b[43mf\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1918\u001b[0m \u001b[43m \u001b[49m\u001b[43mproxies\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mproxies\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1919\u001b[0m \u001b[43m \u001b[49m\u001b[43mresume_size\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mresume_size\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1920\u001b[0m \u001b[43m \u001b[49m\u001b[43mheaders\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mheaders\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1921\u001b[0m \u001b[43m \u001b[49m\u001b[43mexpected_size\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mexpected_size\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1922\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1924\u001b[0m logger\u001b[38;5;241m.\u001b[39minfo(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mDownload complete. Moving file to \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mdestination_path\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m 1925\u001b[0m _chmod_and_move(incomplete_path, destination_path)\n",
|
| 454 |
+
"File \u001b[0;32m/usr/local/lib/python3.10/dist-packages/huggingface_hub/file_download.py:549\u001b[0m, in \u001b[0;36mhttp_get\u001b[0;34m(url, temp_file, proxies, resume_size, headers, expected_size, displayed_filename, _nb_retries, _tqdm_bar)\u001b[0m\n\u001b[1;32m 547\u001b[0m new_resume_size \u001b[38;5;241m=\u001b[39m resume_size\n\u001b[1;32m 548\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 549\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m chunk \u001b[38;5;129;01min\u001b[39;00m r\u001b[38;5;241m.\u001b[39miter_content(chunk_size\u001b[38;5;241m=\u001b[39mDOWNLOAD_CHUNK_SIZE):\n\u001b[1;32m 550\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m chunk: \u001b[38;5;66;03m# filter out keep-alive new chunks\u001b[39;00m\n\u001b[1;32m 551\u001b[0m progress\u001b[38;5;241m.\u001b[39mupdate(\u001b[38;5;28mlen\u001b[39m(chunk))\n",
|
| 455 |
+
"File \u001b[0;32m/usr/local/lib/python3.10/dist-packages/requests/models.py:820\u001b[0m, in \u001b[0;36mResponse.iter_content.<locals>.generate\u001b[0;34m()\u001b[0m\n\u001b[1;32m 818\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mhasattr\u001b[39m(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mraw, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mstream\u001b[39m\u001b[38;5;124m\"\u001b[39m):\n\u001b[1;32m 819\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 820\u001b[0m \u001b[38;5;28;01myield from\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mraw\u001b[38;5;241m.\u001b[39mstream(chunk_size, decode_content\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m)\n\u001b[1;32m 821\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m ProtocolError \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m 822\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m ChunkedEncodingError(e)\n",
|
| 456 |
+
"File \u001b[0;32m/usr/local/lib/python3.10/dist-packages/urllib3/response.py:628\u001b[0m, in \u001b[0;36mHTTPResponse.stream\u001b[0;34m(self, amt, decode_content)\u001b[0m\n\u001b[1;32m 626\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 627\u001b[0m \u001b[38;5;28;01mwhile\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m is_fp_closed(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_fp):\n\u001b[0;32m--> 628\u001b[0m data \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mread\u001b[49m\u001b[43m(\u001b[49m\u001b[43mamt\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mamt\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mdecode_content\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mdecode_content\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 630\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m data:\n\u001b[1;32m 631\u001b[0m \u001b[38;5;28;01myield\u001b[39;00m data\n",
|
| 457 |
+
"File \u001b[0;32m/usr/local/lib/python3.10/dist-packages/urllib3/response.py:567\u001b[0m, in \u001b[0;36mHTTPResponse.read\u001b[0;34m(self, amt, decode_content, cache_content)\u001b[0m\n\u001b[1;32m 564\u001b[0m fp_closed \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mgetattr\u001b[39m(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_fp, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mclosed\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;28;01mFalse\u001b[39;00m)\n\u001b[1;32m 566\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_error_catcher():\n\u001b[0;32m--> 567\u001b[0m data \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_fp_read\u001b[49m\u001b[43m(\u001b[49m\u001b[43mamt\u001b[49m\u001b[43m)\u001b[49m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m fp_closed \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;124mb\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 568\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m amt \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m 569\u001b[0m flush_decoder \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mTrue\u001b[39;00m\n",
|
| 458 |
+
"File \u001b[0;32m/usr/local/lib/python3.10/dist-packages/urllib3/response.py:533\u001b[0m, in \u001b[0;36mHTTPResponse._fp_read\u001b[0;34m(self, amt)\u001b[0m\n\u001b[1;32m 530\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m buffer\u001b[38;5;241m.\u001b[39mgetvalue()\n\u001b[1;32m 531\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 532\u001b[0m \u001b[38;5;66;03m# StringIO doesn't like amt=None\u001b[39;00m\n\u001b[0;32m--> 533\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_fp\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mread\u001b[49m\u001b[43m(\u001b[49m\u001b[43mamt\u001b[49m\u001b[43m)\u001b[49m \u001b[38;5;28;01mif\u001b[39;00m amt \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_fp\u001b[38;5;241m.\u001b[39mread()\n",
|
| 459 |
+
"File \u001b[0;32m/usr/lib/python3.10/http/client.py:466\u001b[0m, in \u001b[0;36mHTTPResponse.read\u001b[0;34m(self, amt)\u001b[0m\n\u001b[1;32m 463\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mlength \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;129;01mand\u001b[39;00m amt \u001b[38;5;241m>\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mlength:\n\u001b[1;32m 464\u001b[0m \u001b[38;5;66;03m# clip the read to the \"end of response\"\u001b[39;00m\n\u001b[1;32m 465\u001b[0m amt \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mlength\n\u001b[0;32m--> 466\u001b[0m s \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfp\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mread\u001b[49m\u001b[43m(\u001b[49m\u001b[43mamt\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 467\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m s \u001b[38;5;129;01mand\u001b[39;00m amt:\n\u001b[1;32m 468\u001b[0m \u001b[38;5;66;03m# Ideally, we would raise IncompleteRead if the content-length\u001b[39;00m\n\u001b[1;32m 469\u001b[0m \u001b[38;5;66;03m# wasn't satisfied, but it might break compatibility.\u001b[39;00m\n\u001b[1;32m 470\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_close_conn()\n",
|
| 460 |
+
"File \u001b[0;32m/usr/lib/python3.10/socket.py:705\u001b[0m, in \u001b[0;36mSocketIO.readinto\u001b[0;34m(self, b)\u001b[0m\n\u001b[1;32m 703\u001b[0m \u001b[38;5;28;01mwhile\u001b[39;00m \u001b[38;5;28;01mTrue\u001b[39;00m:\n\u001b[1;32m 704\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 705\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_sock\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mrecv_into\u001b[49m\u001b[43m(\u001b[49m\u001b[43mb\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 706\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m timeout:\n\u001b[1;32m 707\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_timeout_occurred \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mTrue\u001b[39;00m\n",
|
| 461 |
+
"File \u001b[0;32m/usr/lib/python3.10/ssl.py:1274\u001b[0m, in \u001b[0;36mSSLSocket.recv_into\u001b[0;34m(self, buffer, nbytes, flags)\u001b[0m\n\u001b[1;32m 1270\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m flags \u001b[38;5;241m!=\u001b[39m \u001b[38;5;241m0\u001b[39m:\n\u001b[1;32m 1271\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\n\u001b[1;32m 1272\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mnon-zero flags not allowed in calls to recv_into() on \u001b[39m\u001b[38;5;132;01m%s\u001b[39;00m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;241m%\u001b[39m\n\u001b[1;32m 1273\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__class__\u001b[39m)\n\u001b[0;32m-> 1274\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mread\u001b[49m\u001b[43m(\u001b[49m\u001b[43mnbytes\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mbuffer\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1275\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 1276\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28msuper\u001b[39m()\u001b[38;5;241m.\u001b[39mrecv_into(buffer, nbytes, flags)\n",
|
| 462 |
+
"File \u001b[0;32m/usr/lib/python3.10/ssl.py:1130\u001b[0m, in \u001b[0;36mSSLSocket.read\u001b[0;34m(self, len, buffer)\u001b[0m\n\u001b[1;32m 1128\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m 1129\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m buffer \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[0;32m-> 1130\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_sslobj\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mread\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mlen\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mbuffer\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1131\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 1132\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_sslobj\u001b[38;5;241m.\u001b[39mread(\u001b[38;5;28mlen\u001b[39m)\n",
|
| 463 |
+
"\u001b[0;31mKeyboardInterrupt\u001b[0m: "
|
| 464 |
+
]
|
| 465 |
+
}
|
| 466 |
+
],
|
| 467 |
+
"source": [
|
| 468 |
+
"# Load model directly\n",
|
| 469 |
+
"from transformers import AutoTokenizer, AutoModel\n",
|
| 470 |
+
"\n",
|
| 471 |
+
"tokenizer = AutoTokenizer.from_pretrained(\"OpenOpenAI/checkpoint-2500\")\n",
|
| 472 |
+
"model = AutoModel.from_pretrained(\"OpenOpenAI/checkpoint-2500\")"
|
| 473 |
+
]
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"cell_type": "code",
|
| 477 |
+
"execution_count": 23,
|
| 478 |
+
"id": "0f8a691a-15be-4ce2-9ea1-8758471f5824",
|
| 479 |
+
"metadata": {},
|
| 480 |
+
"outputs": [
|
| 481 |
+
{
|
| 482 |
+
"name": "stdout",
|
| 483 |
+
"output_type": "stream",
|
| 484 |
+
"text": [
|
| 485 |
+
"PhiModel(\n",
|
| 486 |
+
" (embed_tokens): Embedding(51200, 2048)\n",
|
| 487 |
+
" (embed_dropout): Dropout(p=0.0, inplace=False)\n",
|
| 488 |
+
" (layers): ModuleList(\n",
|
| 489 |
+
" (0-23): 24 x PhiDecoderLayer(\n",
|
| 490 |
+
" (self_attn): PhiAttention(\n",
|
| 491 |
+
" (q_proj): Linear(in_features=2048, out_features=2048, bias=True)\n",
|
| 492 |
+
" (k_proj): Linear(in_features=2048, out_features=2048, bias=True)\n",
|
| 493 |
+
" (v_proj): Linear(in_features=2048, out_features=2048, bias=True)\n",
|
| 494 |
+
" (dense): Linear(in_features=2048, out_features=2048, bias=True)\n",
|
| 495 |
+
" (rotary_emb): PhiRotaryEmbedding()\n",
|
| 496 |
+
" )\n",
|
| 497 |
+
" (mlp): PhiMLP(\n",
|
| 498 |
+
" (activation_fn): NewGELUActivation()\n",
|
| 499 |
+
" (fc1): Linear(in_features=2048, out_features=8192, bias=True)\n",
|
| 500 |
+
" (fc2): Linear(in_features=8192, out_features=2048, bias=True)\n",
|
| 501 |
+
" )\n",
|
| 502 |
+
" (input_layernorm): LayerNorm((2048,), eps=1e-05, elementwise_affine=True)\n",
|
| 503 |
+
" (resid_dropout): Dropout(p=0.0, inplace=False)\n",
|
| 504 |
+
" )\n",
|
| 505 |
+
" )\n",
|
| 506 |
+
" (final_layernorm): LayerNorm((2048,), eps=1e-05, elementwise_affine=True)\n",
|
| 507 |
+
")\n"
|
| 508 |
+
]
|
| 509 |
+
}
|
| 510 |
+
],
|
| 511 |
+
"source": [
|
| 512 |
+
"print(model)"
|
| 513 |
+
]
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"cell_type": "code",
|
| 517 |
+
"execution_count": 13,
|
| 518 |
+
"id": "9da6361a-e291-4a91-a942-676f84292c43",
|
| 519 |
+
"metadata": {},
|
| 520 |
+
"outputs": [
|
| 521 |
+
{
|
| 522 |
+
"ename": "OSError",
|
| 523 |
+
"evalue": "Can't load tokenizer for 'OpenOpenAI/checkpoint-2500'. If you were trying to load it from 'https://huggingface.co/models', make sure you don't have a local directory with the same name. Otherwise, make sure 'OpenOpenAI/checkpoint-2500' is the correct path to a directory containing all relevant files for a CodeGenTokenizerFast tokenizer.",
|
| 524 |
+
"output_type": "error",
|
| 525 |
+
"traceback": [
|
| 526 |
+
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
|
| 527 |
+
"\u001b[0;31mOSError\u001b[0m Traceback (most recent call last)",
|
| 528 |
+
"Cell \u001b[0;32mIn[13], line 5\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtransformers\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m AutoTokenizer, AutoModel\n\u001b[1;32m 3\u001b[0m model_name \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mOpenOpenAI/checkpoint-2500\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;66;03m# Replace with the correct path\u001b[39;00m\n\u001b[0;32m----> 5\u001b[0m tokenizer \u001b[38;5;241m=\u001b[39m \u001b[43mAutoTokenizer\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfrom_pretrained\u001b[49m\u001b[43m(\u001b[49m\u001b[43mmodel_name\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 6\u001b[0m model \u001b[38;5;241m=\u001b[39m AutoModel\u001b[38;5;241m.\u001b[39mfrom_pretrained(model_name)\n",
|
| 529 |
+
"File \u001b[0;32m/usr/local/lib/python3.10/dist-packages/transformers/models/auto/tokenization_auto.py:915\u001b[0m, in \u001b[0;36mAutoTokenizer.from_pretrained\u001b[0;34m(cls, pretrained_model_name_or_path, *inputs, **kwargs)\u001b[0m\n\u001b[1;32m 912\u001b[0m tokenizer_class_py, tokenizer_class_fast \u001b[38;5;241m=\u001b[39m TOKENIZER_MAPPING[\u001b[38;5;28mtype\u001b[39m(config)]\n\u001b[1;32m 914\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m tokenizer_class_fast \u001b[38;5;129;01mand\u001b[39;00m (use_fast \u001b[38;5;129;01mor\u001b[39;00m tokenizer_class_py \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m):\n\u001b[0;32m--> 915\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mtokenizer_class_fast\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfrom_pretrained\u001b[49m\u001b[43m(\u001b[49m\u001b[43mpretrained_model_name_or_path\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43minputs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 916\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 917\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m tokenizer_class_py \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n",
|
| 530 |
+
"File \u001b[0;32m/usr/local/lib/python3.10/dist-packages/transformers/tokenization_utils_base.py:2275\u001b[0m, in \u001b[0;36mPreTrainedTokenizerBase.from_pretrained\u001b[0;34m(cls, pretrained_model_name_or_path, cache_dir, force_download, local_files_only, token, revision, trust_remote_code, *init_inputs, **kwargs)\u001b[0m\n\u001b[1;32m 2272\u001b[0m \u001b[38;5;66;03m# If one passes a GGUF file path to `gguf_file` there is no need for this check as the tokenizer will be\u001b[39;00m\n\u001b[1;32m 2273\u001b[0m \u001b[38;5;66;03m# loaded directly from the GGUF file.\u001b[39;00m\n\u001b[1;32m 2274\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mall\u001b[39m(full_file_name \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;28;01mfor\u001b[39;00m full_file_name \u001b[38;5;129;01min\u001b[39;00m resolved_vocab_files\u001b[38;5;241m.\u001b[39mvalues()) \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m gguf_file:\n\u001b[0;32m-> 2275\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mEnvironmentError\u001b[39;00m(\n\u001b[1;32m 2276\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mCan\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mt load tokenizer for \u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mpretrained_model_name_or_path\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m. If you were trying to load it from \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 2277\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mhttps://huggingface.co/models\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m, make sure you don\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mt have a local directory with the same name. \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 2278\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mOtherwise, make sure \u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mpretrained_model_name_or_path\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m is the correct path to a directory \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 2279\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mcontaining all relevant files for a \u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;28mcls\u001b[39m\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__name__\u001b[39m\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m tokenizer.\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 2280\u001b[0m )\n\u001b[1;32m 2282\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m file_id, file_path \u001b[38;5;129;01min\u001b[39;00m vocab_files\u001b[38;5;241m.\u001b[39mitems():\n\u001b[1;32m 2283\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m file_id \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m resolved_vocab_files:\n",
|
| 531 |
+
"\u001b[0;31mOSError\u001b[0m: Can't load tokenizer for 'OpenOpenAI/checkpoint-2500'. If you were trying to load it from 'https://huggingface.co/models', make sure you don't have a local directory with the same name. Otherwise, make sure 'OpenOpenAI/checkpoint-2500' is the correct path to a directory containing all relevant files for a CodeGenTokenizerFast tokenizer."
|
| 532 |
+
]
|
| 533 |
+
}
|
| 534 |
+
],
|
| 535 |
+
"source": [
|
| 536 |
+
"from transformers import AutoTokenizer, AutoModel\n",
|
| 537 |
+
"\n",
|
| 538 |
+
"model_name = \"OpenOpenAI/checkpoint-2500\" # Replace with the correct path\n",
|
| 539 |
+
"\n",
|
| 540 |
+
"tokenizer = AutoTokenizer.from_pretrained(model_name)\n",
|
| 541 |
+
"model = AutoModel.from_pretrained(model_name)"
|
| 542 |
+
]
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"cell_type": "code",
|
| 546 |
+
"execution_count": 25,
|
| 547 |
+
"id": "0da6e77a-bfb1-4e24-af67-1b76009f7289",
|
| 548 |
+
"metadata": {},
|
| 549 |
+
"outputs": [
|
| 550 |
+
{
|
| 551 |
+
"name": "stdout",
|
| 552 |
+
"output_type": "stream",
|
| 553 |
+
"text": [
|
| 554 |
+
"4.43.1\n"
|
| 555 |
+
]
|
| 556 |
+
}
|
| 557 |
+
],
|
| 558 |
+
"source": [
|
| 559 |
+
"import transformers\n",
|
| 560 |
+
"print(transformers.__version__)"
|
| 561 |
+
]
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"cell_type": "code",
|
| 565 |
+
"execution_count": null,
|
| 566 |
+
"id": "528f1b39-10d8-4d17-939e-5fb82c06223b",
|
| 567 |
+
"metadata": {},
|
| 568 |
+
"outputs": [],
|
| 569 |
+
"source": []
|
| 570 |
+
}
|
| 571 |
+
],
|
| 572 |
+
"metadata": {
|
| 573 |
+
"kernelspec": {
|
| 574 |
+
"display_name": "Python 3 (ipykernel)",
|
| 575 |
+
"language": "python",
|
| 576 |
+
"name": "python3"
|
| 577 |
+
},
|
| 578 |
+
"language_info": {
|
| 579 |
+
"codemirror_mode": {
|
| 580 |
+
"name": "ipython",
|
| 581 |
+
"version": 3
|
| 582 |
+
},
|
| 583 |
+
"file_extension": ".py",
|
| 584 |
+
"mimetype": "text/x-python",
|
| 585 |
+
"name": "python",
|
| 586 |
+
"nbconvert_exporter": "python",
|
| 587 |
+
"pygments_lexer": "ipython3",
|
| 588 |
+
"version": "3.10.12"
|
| 589 |
+
}
|
| 590 |
+
},
|
| 591 |
+
"nbformat": 4,
|
| 592 |
+
"nbformat_minor": 5
|
| 593 |
+
}
|
added_tokens.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"\t\t": 50294,
|
| 3 |
+
"\t\t\t": 50293,
|
| 4 |
+
"\t\t\t\t": 50292,
|
| 5 |
+
"\t\t\t\t\t": 50291,
|
| 6 |
+
"\t\t\t\t\t\t": 50290,
|
| 7 |
+
"\t\t\t\t\t\t\t": 50289,
|
| 8 |
+
"\t\t\t\t\t\t\t\t": 50288,
|
| 9 |
+
"\t\t\t\t\t\t\t\t\t": 50287,
|
| 10 |
+
" ": 50286,
|
| 11 |
+
" ": 50285,
|
| 12 |
+
" ": 50284,
|
| 13 |
+
" ": 50283,
|
| 14 |
+
" ": 50282,
|
| 15 |
+
" ": 50281,
|
| 16 |
+
" ": 50280,
|
| 17 |
+
" ": 50279,
|
| 18 |
+
" ": 50278,
|
| 19 |
+
" ": 50277,
|
| 20 |
+
" ": 50276,
|
| 21 |
+
" ": 50275,
|
| 22 |
+
" ": 50274,
|
| 23 |
+
" ": 50273,
|
| 24 |
+
" ": 50272,
|
| 25 |
+
" ": 50271,
|
| 26 |
+
" ": 50270,
|
| 27 |
+
" ": 50269,
|
| 28 |
+
" ": 50268,
|
| 29 |
+
" ": 50267,
|
| 30 |
+
" ": 50266,
|
| 31 |
+
" ": 50265,
|
| 32 |
+
" ": 50264,
|
| 33 |
+
" ": 50263,
|
| 34 |
+
" ": 50262,
|
| 35 |
+
" ": 50261,
|
| 36 |
+
" ": 50260,
|
| 37 |
+
" ": 50259,
|
| 38 |
+
" ": 50258,
|
| 39 |
+
" ": 50257
|
| 40 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/phi-1_5",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"PhiForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": null,
|
| 8 |
+
"embd_pdrop": 0.0,
|
| 9 |
+
"eos_token_id": null,
|
| 10 |
+
"hidden_act": "gelu_new",
|
| 11 |
+
"hidden_size": 2048,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 8192,
|
| 14 |
+
"layer_norm_eps": 1e-05,
|
| 15 |
+
"max_position_embeddings": 2048,
|
| 16 |
+
"model_type": "phi",
|
| 17 |
+
"num_attention_heads": 32,
|
| 18 |
+
"num_hidden_layers": 24,
|
| 19 |
+
"num_key_value_heads": 32,
|
| 20 |
+
"partial_rotary_factor": 0.5,
|
| 21 |
+
"qk_layernorm": false,
|
| 22 |
+
"resid_pdrop": 0.0,
|
| 23 |
+
"rope_scaling": null,
|
| 24 |
+
"rope_theta": 10000.0,
|
| 25 |
+
"tie_word_embeddings": false,
|
| 26 |
+
"torch_dtype": "float32",
|
| 27 |
+
"transformers_version": "4.44.0",
|
| 28 |
+
"use_cache": true,
|
| 29 |
+
"vocab_size": 51200
|
| 30 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"transformers_version": "4.44.0"
|
| 4 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:128e396b3aa3c9e172a9ec8d07eacfeb9c787a1fe5a47d14e7665982ca0206bf
|
| 3 |
+
size 4984916152
|
model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d10669ad60fb8ac3a3d03211ba8aa57195c7b112a47190fefe794af0f701482f
|
| 3 |
+
size 688204064
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,348 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 5673082880
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.bias": "model-00002-of-00002.safetensors",
|
| 7 |
+
"lm_head.weight": "model-00002-of-00002.safetensors",
|
| 8 |
+
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 9 |
+
"model.final_layernorm.bias": "model-00002-of-00002.safetensors",
|
| 10 |
+
"model.final_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 11 |
+
"model.layers.0.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 12 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 13 |
+
"model.layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 14 |
+
"model.layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 15 |
+
"model.layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 16 |
+
"model.layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 18 |
+
"model.layers.0.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 19 |
+
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 20 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 21 |
+
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 22 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 23 |
+
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 24 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 25 |
+
"model.layers.1.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 26 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 27 |
+
"model.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 28 |
+
"model.layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 29 |
+
"model.layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 30 |
+
"model.layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 31 |
+
"model.layers.1.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 32 |
+
"model.layers.1.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 33 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 34 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 35 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 36 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 37 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 38 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 39 |
+
"model.layers.10.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 40 |
+
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 41 |
+
"model.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 42 |
+
"model.layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 43 |
+
"model.layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 44 |
+
"model.layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 45 |
+
"model.layers.10.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 46 |
+
"model.layers.10.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 47 |
+
"model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 48 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 49 |
+
"model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 50 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 51 |
+
"model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 52 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 53 |
+
"model.layers.11.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 54 |
+
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 55 |
+
"model.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 56 |
+
"model.layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 57 |
+
"model.layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 58 |
+
"model.layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 59 |
+
"model.layers.11.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 60 |
+
"model.layers.11.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 61 |
+
"model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 62 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 63 |
+
"model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 64 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 65 |
+
"model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 66 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 67 |
+
"model.layers.12.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 68 |
+
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 69 |
+
"model.layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 70 |
+
"model.layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 71 |
+
"model.layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 72 |
+
"model.layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 73 |
+
"model.layers.12.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 74 |
+
"model.layers.12.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 75 |
+
"model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 76 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 77 |
+
"model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 78 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 79 |
+
"model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 80 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 81 |
+
"model.layers.13.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 82 |
+
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 83 |
+
"model.layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 84 |
+
"model.layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 85 |
+
"model.layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 86 |
+
"model.layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 87 |
+
"model.layers.13.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 88 |
+
"model.layers.13.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 89 |
+
"model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 90 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 91 |
+
"model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 92 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 93 |
+
"model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 94 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 95 |
+
"model.layers.14.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 96 |
+
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 97 |
+
"model.layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 98 |
+
"model.layers.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 99 |
+
"model.layers.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 100 |
+
"model.layers.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 101 |
+
"model.layers.14.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 102 |
+
"model.layers.14.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 103 |
+
"model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 104 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 105 |
+
"model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 106 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 107 |
+
"model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 108 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 109 |
+
"model.layers.15.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 110 |
+
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 111 |
+
"model.layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 112 |
+
"model.layers.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 113 |
+
"model.layers.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 114 |
+
"model.layers.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 115 |
+
"model.layers.15.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 116 |
+
"model.layers.15.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 117 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 118 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 119 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 120 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 121 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 122 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 123 |
+
"model.layers.16.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 124 |
+
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 125 |
+
"model.layers.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 126 |
+
"model.layers.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 127 |
+
"model.layers.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 128 |
+
"model.layers.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 129 |
+
"model.layers.16.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 130 |
+
"model.layers.16.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 131 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 132 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 133 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 134 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 135 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 136 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 137 |
+
"model.layers.17.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 138 |
+
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 139 |
+
"model.layers.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 140 |
+
"model.layers.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 141 |
+
"model.layers.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 142 |
+
"model.layers.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 143 |
+
"model.layers.17.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 144 |
+
"model.layers.17.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 145 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 146 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 147 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 148 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 149 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 150 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 151 |
+
"model.layers.18.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 152 |
+
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 153 |
+
"model.layers.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 154 |
+
"model.layers.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 155 |
+
"model.layers.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 156 |
+
"model.layers.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 157 |
+
"model.layers.18.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 158 |
+
"model.layers.18.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 159 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 160 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 161 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 162 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 163 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 164 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 165 |
+
"model.layers.19.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 166 |
+
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 167 |
+
"model.layers.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 168 |
+
"model.layers.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 169 |
+
"model.layers.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 170 |
+
"model.layers.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 171 |
+
"model.layers.19.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 172 |
+
"model.layers.19.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 173 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 174 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 175 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 176 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 177 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 178 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 179 |
+
"model.layers.2.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 180 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 181 |
+
"model.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 182 |
+
"model.layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 183 |
+
"model.layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 184 |
+
"model.layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 185 |
+
"model.layers.2.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 186 |
+
"model.layers.2.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 187 |
+
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 188 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 189 |
+
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 190 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 191 |
+
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 192 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 193 |
+
"model.layers.20.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 194 |
+
"model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 195 |
+
"model.layers.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 196 |
+
"model.layers.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 197 |
+
"model.layers.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 198 |
+
"model.layers.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 199 |
+
"model.layers.20.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 200 |
+
"model.layers.20.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 201 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 202 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 203 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 204 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 205 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 206 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 207 |
+
"model.layers.21.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 208 |
+
"model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 209 |
+
"model.layers.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 210 |
+
"model.layers.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 211 |
+
"model.layers.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 212 |
+
"model.layers.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 213 |
+
"model.layers.21.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 214 |
+
"model.layers.21.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 215 |
+
"model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 216 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 217 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 218 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 219 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 220 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 221 |
+
"model.layers.22.input_layernorm.bias": "model-00002-of-00002.safetensors",
|
| 222 |
+
"model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 223 |
+
"model.layers.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 224 |
+
"model.layers.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 225 |
+
"model.layers.22.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 226 |
+
"model.layers.22.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 227 |
+
"model.layers.22.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 228 |
+
"model.layers.22.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 229 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 230 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 231 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 232 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 233 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 234 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 235 |
+
"model.layers.23.input_layernorm.bias": "model-00002-of-00002.safetensors",
|
| 236 |
+
"model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 237 |
+
"model.layers.23.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 238 |
+
"model.layers.23.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 239 |
+
"model.layers.23.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 240 |
+
"model.layers.23.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 241 |
+
"model.layers.23.self_attn.dense.bias": "model-00002-of-00002.safetensors",
|
| 242 |
+
"model.layers.23.self_attn.dense.weight": "model-00002-of-00002.safetensors",
|
| 243 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 244 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 245 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 246 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 247 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 248 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 249 |
+
"model.layers.3.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 250 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 251 |
+
"model.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 252 |
+
"model.layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 253 |
+
"model.layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 254 |
+
"model.layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 255 |
+
"model.layers.3.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 256 |
+
"model.layers.3.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 257 |
+
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 258 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 259 |
+
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 260 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 261 |
+
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 262 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 263 |
+
"model.layers.4.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 264 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 265 |
+
"model.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 266 |
+
"model.layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 267 |
+
"model.layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 268 |
+
"model.layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 269 |
+
"model.layers.4.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 270 |
+
"model.layers.4.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 271 |
+
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 272 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 273 |
+
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 274 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 275 |
+
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 276 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 277 |
+
"model.layers.5.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 278 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 279 |
+
"model.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 280 |
+
"model.layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 281 |
+
"model.layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 282 |
+
"model.layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 283 |
+
"model.layers.5.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 284 |
+
"model.layers.5.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 285 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 286 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 287 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 288 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 289 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 290 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 291 |
+
"model.layers.6.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 292 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 293 |
+
"model.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 294 |
+
"model.layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 295 |
+
"model.layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 296 |
+
"model.layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 297 |
+
"model.layers.6.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 298 |
+
"model.layers.6.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 299 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 300 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 301 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 302 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 303 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 304 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 305 |
+
"model.layers.7.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 306 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 307 |
+
"model.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 308 |
+
"model.layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 309 |
+
"model.layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 310 |
+
"model.layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 311 |
+
"model.layers.7.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 312 |
+
"model.layers.7.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 313 |
+
"model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 314 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 315 |
+
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 316 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 317 |
+
"model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 318 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 319 |
+
"model.layers.8.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 320 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 321 |
+
"model.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 322 |
+
"model.layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 323 |
+
"model.layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 324 |
+
"model.layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 325 |
+
"model.layers.8.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 326 |
+
"model.layers.8.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 327 |
+
"model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 328 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 329 |
+
"model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 330 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 331 |
+
"model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 332 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 333 |
+
"model.layers.9.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 334 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 335 |
+
"model.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 336 |
+
"model.layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 337 |
+
"model.layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 338 |
+
"model.layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 339 |
+
"model.layers.9.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 340 |
+
"model.layers.9.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 341 |
+
"model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 342 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 343 |
+
"model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 344 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 345 |
+
"model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 346 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors"
|
| 347 |
+
}
|
| 348 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:78eb917a57d03b385da971fa844e0db8a187a35335e36a1bc0e82e92302dd188
|
| 3 |
+
size 11346461349
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9196a1e708bf24d6abba41cce3f8558820acc3e50f9394c5955e29eb41ffea3d
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ce0598b42c3185859e3160b65043f9cfce81ce16cf2ef53e29340c5babc94362
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|endoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<|endoftext|>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<|endoftext|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,325 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"50256": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"50257": {
|
| 13 |
+
"content": " ",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": false
|
| 19 |
+
},
|
| 20 |
+
"50258": {
|
| 21 |
+
"content": " ",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": false
|
| 27 |
+
},
|
| 28 |
+
"50259": {
|
| 29 |
+
"content": " ",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": false
|
| 35 |
+
},
|
| 36 |
+
"50260": {
|
| 37 |
+
"content": " ",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": true,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": false
|
| 43 |
+
},
|
| 44 |
+
"50261": {
|
| 45 |
+
"content": " ",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": false
|
| 51 |
+
},
|
| 52 |
+
"50262": {
|
| 53 |
+
"content": " ",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": true,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": false
|
| 59 |
+
},
|
| 60 |
+
"50263": {
|
| 61 |
+
"content": " ",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": true,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": false
|
| 67 |
+
},
|
| 68 |
+
"50264": {
|
| 69 |
+
"content": " ",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": true,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": false
|
| 75 |
+
},
|
| 76 |
+
"50265": {
|
| 77 |
+
"content": " ",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": true,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": false
|
| 83 |
+
},
|
| 84 |
+
"50266": {
|
| 85 |
+
"content": " ",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": true,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": false
|
| 91 |
+
},
|
| 92 |
+
"50267": {
|
| 93 |
+
"content": " ",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": true,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": false
|
| 99 |
+
},
|
| 100 |
+
"50268": {
|
| 101 |
+
"content": " ",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": true,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": false
|
| 107 |
+
},
|
| 108 |
+
"50269": {
|
| 109 |
+
"content": " ",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": true,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": false
|
| 115 |
+
},
|
| 116 |
+
"50270": {
|
| 117 |
+
"content": " ",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": true,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": false
|
| 123 |
+
},
|
| 124 |
+
"50271": {
|
| 125 |
+
"content": " ",
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"normalized": true,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": false
|
| 131 |
+
},
|
| 132 |
+
"50272": {
|
| 133 |
+
"content": " ",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": true,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": false
|
| 139 |
+
},
|
| 140 |
+
"50273": {
|
| 141 |
+
"content": " ",
|
| 142 |
+
"lstrip": false,
|
| 143 |
+
"normalized": true,
|
| 144 |
+
"rstrip": false,
|
| 145 |
+
"single_word": false,
|
| 146 |
+
"special": false
|
| 147 |
+
},
|
| 148 |
+
"50274": {
|
| 149 |
+
"content": " ",
|
| 150 |
+
"lstrip": false,
|
| 151 |
+
"normalized": true,
|
| 152 |
+
"rstrip": false,
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"special": false
|
| 155 |
+
},
|
| 156 |
+
"50275": {
|
| 157 |
+
"content": " ",
|
| 158 |
+
"lstrip": false,
|
| 159 |
+
"normalized": true,
|
| 160 |
+
"rstrip": false,
|
| 161 |
+
"single_word": false,
|
| 162 |
+
"special": false
|
| 163 |
+
},
|
| 164 |
+
"50276": {
|
| 165 |
+
"content": " ",
|
| 166 |
+
"lstrip": false,
|
| 167 |
+
"normalized": true,
|
| 168 |
+
"rstrip": false,
|
| 169 |
+
"single_word": false,
|
| 170 |
+
"special": false
|
| 171 |
+
},
|
| 172 |
+
"50277": {
|
| 173 |
+
"content": " ",
|
| 174 |
+
"lstrip": false,
|
| 175 |
+
"normalized": true,
|
| 176 |
+
"rstrip": false,
|
| 177 |
+
"single_word": false,
|
| 178 |
+
"special": false
|
| 179 |
+
},
|
| 180 |
+
"50278": {
|
| 181 |
+
"content": " ",
|
| 182 |
+
"lstrip": false,
|
| 183 |
+
"normalized": true,
|
| 184 |
+
"rstrip": false,
|
| 185 |
+
"single_word": false,
|
| 186 |
+
"special": false
|
| 187 |
+
},
|
| 188 |
+
"50279": {
|
| 189 |
+
"content": " ",
|
| 190 |
+
"lstrip": false,
|
| 191 |
+
"normalized": true,
|
| 192 |
+
"rstrip": false,
|
| 193 |
+
"single_word": false,
|
| 194 |
+
"special": false
|
| 195 |
+
},
|
| 196 |
+
"50280": {
|
| 197 |
+
"content": " ",
|
| 198 |
+
"lstrip": false,
|
| 199 |
+
"normalized": true,
|
| 200 |
+
"rstrip": false,
|
| 201 |
+
"single_word": false,
|
| 202 |
+
"special": false
|
| 203 |
+
},
|
| 204 |
+
"50281": {
|
| 205 |
+
"content": " ",
|
| 206 |
+
"lstrip": false,
|
| 207 |
+
"normalized": true,
|
| 208 |
+
"rstrip": false,
|
| 209 |
+
"single_word": false,
|
| 210 |
+
"special": false
|
| 211 |
+
},
|
| 212 |
+
"50282": {
|
| 213 |
+
"content": " ",
|
| 214 |
+
"lstrip": false,
|
| 215 |
+
"normalized": true,
|
| 216 |
+
"rstrip": false,
|
| 217 |
+
"single_word": false,
|
| 218 |
+
"special": false
|
| 219 |
+
},
|
| 220 |
+
"50283": {
|
| 221 |
+
"content": " ",
|
| 222 |
+
"lstrip": false,
|
| 223 |
+
"normalized": true,
|
| 224 |
+
"rstrip": false,
|
| 225 |
+
"single_word": false,
|
| 226 |
+
"special": false
|
| 227 |
+
},
|
| 228 |
+
"50284": {
|
| 229 |
+
"content": " ",
|
| 230 |
+
"lstrip": false,
|
| 231 |
+
"normalized": true,
|
| 232 |
+
"rstrip": false,
|
| 233 |
+
"single_word": false,
|
| 234 |
+
"special": false
|
| 235 |
+
},
|
| 236 |
+
"50285": {
|
| 237 |
+
"content": " ",
|
| 238 |
+
"lstrip": false,
|
| 239 |
+
"normalized": true,
|
| 240 |
+
"rstrip": false,
|
| 241 |
+
"single_word": false,
|
| 242 |
+
"special": false
|
| 243 |
+
},
|
| 244 |
+
"50286": {
|
| 245 |
+
"content": " ",
|
| 246 |
+
"lstrip": false,
|
| 247 |
+
"normalized": true,
|
| 248 |
+
"rstrip": false,
|
| 249 |
+
"single_word": false,
|
| 250 |
+
"special": false
|
| 251 |
+
},
|
| 252 |
+
"50287": {
|
| 253 |
+
"content": "\t\t\t\t\t\t\t\t\t",
|
| 254 |
+
"lstrip": false,
|
| 255 |
+
"normalized": true,
|
| 256 |
+
"rstrip": false,
|
| 257 |
+
"single_word": false,
|
| 258 |
+
"special": false
|
| 259 |
+
},
|
| 260 |
+
"50288": {
|
| 261 |
+
"content": "\t\t\t\t\t\t\t\t",
|
| 262 |
+
"lstrip": false,
|
| 263 |
+
"normalized": true,
|
| 264 |
+
"rstrip": false,
|
| 265 |
+
"single_word": false,
|
| 266 |
+
"special": false
|
| 267 |
+
},
|
| 268 |
+
"50289": {
|
| 269 |
+
"content": "\t\t\t\t\t\t\t",
|
| 270 |
+
"lstrip": false,
|
| 271 |
+
"normalized": true,
|
| 272 |
+
"rstrip": false,
|
| 273 |
+
"single_word": false,
|
| 274 |
+
"special": false
|
| 275 |
+
},
|
| 276 |
+
"50290": {
|
| 277 |
+
"content": "\t\t\t\t\t\t",
|
| 278 |
+
"lstrip": false,
|
| 279 |
+
"normalized": true,
|
| 280 |
+
"rstrip": false,
|
| 281 |
+
"single_word": false,
|
| 282 |
+
"special": false
|
| 283 |
+
},
|
| 284 |
+
"50291": {
|
| 285 |
+
"content": "\t\t\t\t\t",
|
| 286 |
+
"lstrip": false,
|
| 287 |
+
"normalized": true,
|
| 288 |
+
"rstrip": false,
|
| 289 |
+
"single_word": false,
|
| 290 |
+
"special": false
|
| 291 |
+
},
|
| 292 |
+
"50292": {
|
| 293 |
+
"content": "\t\t\t\t",
|
| 294 |
+
"lstrip": false,
|
| 295 |
+
"normalized": true,
|
| 296 |
+
"rstrip": false,
|
| 297 |
+
"single_word": false,
|
| 298 |
+
"special": false
|
| 299 |
+
},
|
| 300 |
+
"50293": {
|
| 301 |
+
"content": "\t\t\t",
|
| 302 |
+
"lstrip": false,
|
| 303 |
+
"normalized": true,
|
| 304 |
+
"rstrip": false,
|
| 305 |
+
"single_word": false,
|
| 306 |
+
"special": false
|
| 307 |
+
},
|
| 308 |
+
"50294": {
|
| 309 |
+
"content": "\t\t",
|
| 310 |
+
"lstrip": false,
|
| 311 |
+
"normalized": true,
|
| 312 |
+
"rstrip": false,
|
| 313 |
+
"single_word": false,
|
| 314 |
+
"special": false
|
| 315 |
+
}
|
| 316 |
+
},
|
| 317 |
+
"bos_token": "<|endoftext|>",
|
| 318 |
+
"clean_up_tokenization_spaces": true,
|
| 319 |
+
"eos_token": "<|endoftext|>",
|
| 320 |
+
"model_max_length": 2048,
|
| 321 |
+
"pad_token": "<|endoftext|>",
|
| 322 |
+
"return_token_type_ids": false,
|
| 323 |
+
"tokenizer_class": "CodeGenTokenizer",
|
| 324 |
+
"unk_token": "<|endoftext|>"
|
| 325 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.5,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 2500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.5,
|
| 13 |
+
"grad_norm": 1.8131240606307983,
|
| 14 |
+
"learning_rate": 4.166666666666667e-05,
|
| 15 |
+
"loss": 2.8997,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.0,
|
| 20 |
+
"grad_norm": 1.7417197227478027,
|
| 21 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 22 |
+
"loss": 2.8097,
|
| 23 |
+
"step": 1000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 1.5,
|
| 27 |
+
"grad_norm": 2.1385185718536377,
|
| 28 |
+
"learning_rate": 2.5e-05,
|
| 29 |
+
"loss": 1.9273,
|
| 30 |
+
"step": 1500
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 2.0,
|
| 34 |
+
"grad_norm": 2.487093448638916,
|
| 35 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 36 |
+
"loss": 1.9087,
|
| 37 |
+
"step": 2000
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 2.5,
|
| 41 |
+
"grad_norm": 2.675701856613159,
|
| 42 |
+
"learning_rate": 8.333333333333334e-06,
|
| 43 |
+
"loss": 1.0467,
|
| 44 |
+
"step": 2500
|
| 45 |
+
}
|
| 46 |
+
],
|
| 47 |
+
"logging_steps": 500,
|
| 48 |
+
"max_steps": 3000,
|
| 49 |
+
"num_input_tokens_seen": 0,
|
| 50 |
+
"num_train_epochs": 3,
|
| 51 |
+
"save_steps": 500,
|
| 52 |
+
"stateful_callbacks": {
|
| 53 |
+
"TrainerControl": {
|
| 54 |
+
"args": {
|
| 55 |
+
"should_epoch_stop": false,
|
| 56 |
+
"should_evaluate": false,
|
| 57 |
+
"should_log": false,
|
| 58 |
+
"should_save": true,
|
| 59 |
+
"should_training_stop": false
|
| 60 |
+
},
|
| 61 |
+
"attributes": {}
|
| 62 |
+
}
|
| 63 |
+
},
|
| 64 |
+
"total_flos": 4.016131522265088e+16,
|
| 65 |
+
"train_batch_size": 8,
|
| 66 |
+
"trial_name": null,
|
| 67 |
+
"trial_params": null
|
| 68 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2b7a8beb226ab77bdefbae34ce5e59335bbf8ec896ef88a2d2c9eb8bf803cfd1
|
| 3 |
+
size 5368
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|