mirror of
https://github.com/wassname/discovering_latent_knowledge.git
synced 2026-09-09 11:21:22 +08:00
fix the id_n thing
distinguish between _No and No
This commit is contained in:
deep1
@@ -63,3 +63,9 @@ Maybe with
|
||||
- manual pruning of generations?
|
||||
|
||||
I guess this shows they they trained whether the text it read is true... because that's much simpler
|
||||
|
||||
|
||||
# 2023-05-28 16:46:38
|
||||
|
||||
bug: so there are two no tokens... wtf
|
||||
the model only uses one! wtf!
|
||||
|
||||
@@ -161,6 +161,218 @@
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"application/vnd.jupyter.widget-view+json": {
|
||||
"model_id": "f663d43afc664db0af519307cb74c698",
|
||||
"version_major": 2,
|
||||
"version_minor": 0
|
||||
},
|
||||
"text/plain": [
|
||||
"Downloading (…)l-00002-of-00007.bin: 0%| | 0.00/9.96G [00:00<?, ?B/s]"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"application/vnd.jupyter.widget-view+json": {
|
||||
"model_id": "0445cbbc58e24fd88395a18756e6d516",
|
||||
"version_major": 2,
|
||||
"version_minor": 0
|
||||
},
|
||||
"text/plain": [
|
||||
"Downloading (…)l-00003-of-00007.bin: 0%| | 0.00/9.90G [00:00<?, ?B/s]"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"application/vnd.jupyter.widget-view+json": {
|
||||
"model_id": "65cf438af6ce4887b3ecb9a5874754aa",
|
||||
"version_major": 2,
|
||||
"version_minor": 0
|
||||
},
|
||||
"text/plain": [
|
||||
"Downloading (…)l-00004-of-00007.bin: 0%| | 0.00/9.87G [00:00<?, ?B/s]"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"application/vnd.jupyter.widget-view+json": {
|
||||
"model_id": "e7fdefe03dcf4b2ab6beaa3cbcead860",
|
||||
"version_major": 2,
|
||||
"version_minor": 0
|
||||
},
|
||||
"text/plain": [
|
||||
"Downloading (…)l-00005-of-00007.bin: 0%| | 0.00/9.87G [00:00<?, ?B/s]"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"application/vnd.jupyter.widget-view+json": {
|
||||
"model_id": "a7c649a67abf4b3ea890e4984b026dea",
|
||||
"version_major": 2,
|
||||
"version_minor": 0
|
||||
},
|
||||
"text/plain": [
|
||||
"Downloading (…)l-00006-of-00007.bin: 0%| | 0.00/9.96G [00:00<?, ?B/s]"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"application/vnd.jupyter.widget-view+json": {
|
||||
"model_id": "0e69d28c9bce48039f13bd1aee482ca0",
|
||||
"version_major": 2,
|
||||
"version_minor": 0
|
||||
},
|
||||
"text/plain": [
|
||||
"Downloading (…)l-00007-of-00007.bin: 0%| | 0.00/5.69G [00:00<?, ?B/s]"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"===================================BUG REPORT===================================\n",
|
||||
"Welcome to bitsandbytes. For bug reports, please run\n",
|
||||
"\n",
|
||||
"python -m bitsandbytes\n",
|
||||
"\n",
|
||||
" and submit this information together with your error trace to: https://github.com/TimDettmers/bitsandbytes/issues\n",
|
||||
"================================================================================\n",
|
||||
"bin /home/ubuntu/mambaforge/envs/dlk2/lib/python3.9/site-packages/bitsandbytes/libbitsandbytes_cuda117.so\n",
|
||||
"CUDA SETUP: CUDA runtime path found: /home/ubuntu/mambaforge/envs/dlk2/lib/libcudart.so\n",
|
||||
"CUDA SETUP: Highest compute capability among GPUs detected: 8.6\n",
|
||||
"CUDA SETUP: Detected CUDA version 117\n",
|
||||
"CUDA SETUP: Loading binary /home/ubuntu/mambaforge/envs/dlk2/lib/python3.9/site-packages/bitsandbytes/libbitsandbytes_cuda117.so...\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"/home/ubuntu/mambaforge/envs/dlk2/lib/python3.9/site-packages/bitsandbytes/cuda_setup/main.py:149: UserWarning: Found duplicate ['libcudart.so', 'libcudart.so.11.0', 'libcudart.so.12.0'] files: {PosixPath('/home/ubuntu/mambaforge/envs/dlk2/lib/libcudart.so'), PosixPath('/home/ubuntu/mambaforge/envs/dlk2/lib/libcudart.so.11.0')}.. We'll flip a coin and try one of these, in order to fail forward.\n",
|
||||
"Either way, this might cause trouble in the future:\n",
|
||||
"If you get `CUDA error: invalid device function` errors, the above might be the cause and the solution is to make sure only one ['libcudart.so', 'libcudart.so.11.0', 'libcudart.so.12.0'] in the paths that we search based on your env.\n",
|
||||
" warn(msg)\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/html": [
|
||||
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #800000; text-decoration-color: #800000\">╭─────────────────────────────── </span><span style=\"color: #800000; text-decoration-color: #800000; font-weight: bold\">Traceback </span><span style=\"color: #bf7f7f; text-decoration-color: #bf7f7f; font-weight: bold\">(most recent call last)</span><span style=\"color: #800000; text-decoration-color: #800000\"> ────────────────────────────────╮</span>\n",
|
||||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> in <span style=\"color: #00ff00; text-decoration-color: #00ff00\"><module></span>:<span style=\"color: #0000ff; text-decoration-color: #0000ff\">26</span> <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> <span style=\"color: #7f7f7f; text-decoration-color: #7f7f7f\">23 </span>lora_repo = <span style=\"color: #0000ff; text-decoration-color: #0000ff\">None</span> <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> <span style=\"color: #7f7f7f; text-decoration-color: #7f7f7f\">24 </span> <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> <span style=\"color: #7f7f7f; text-decoration-color: #7f7f7f\">25 </span>tokenizer = LlamaTokenizer.from_pretrained(model_repo) <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> <span style=\"color: #800000; text-decoration-color: #800000\">❱ </span>26 model = AutoModelForCausalLM.from_pretrained(model_repo, **model_options) <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> <span style=\"color: #7f7f7f; text-decoration-color: #7f7f7f\">27 </span> <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> <span style=\"color: #7f7f7f; text-decoration-color: #7f7f7f\">28 </span><span style=\"color: #0000ff; text-decoration-color: #0000ff\">if</span> lora_repo <span style=\"color: #ff00ff; text-decoration-color: #ff00ff\">is</span> <span style=\"color: #ff00ff; text-decoration-color: #ff00ff\">not</span> <span style=\"color: #0000ff; text-decoration-color: #0000ff\">None</span>: <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> <span style=\"color: #7f7f7f; text-decoration-color: #7f7f7f\">29 </span><span style=\"color: #7f7f7f; text-decoration-color: #7f7f7f\">│ </span><span style=\"color: #7f7f7f; text-decoration-color: #7f7f7f\"># https://github.com/tloen/alpaca-lora/blob/main/generate.py#L40</span> <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> <span style=\"color: #bfbf7f; text-decoration-color: #bfbf7f\">/home/ubuntu/mambaforge/envs/dlk2/lib/python3.9/site-packages/transformers/models/auto/</span><span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">auto_fact</span> <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">ory.py</span>:<span style=\"color: #0000ff; text-decoration-color: #0000ff\">490</span> in <span style=\"color: #00ff00; text-decoration-color: #00ff00\">from_pretrained</span> <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> <span style=\"color: #7f7f7f; text-decoration-color: #7f7f7f\">487 </span><span style=\"color: #7f7f7f; text-decoration-color: #7f7f7f\">│ │ │ </span>) <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> <span style=\"color: #7f7f7f; text-decoration-color: #7f7f7f\">488 </span><span style=\"color: #7f7f7f; text-decoration-color: #7f7f7f\">│ │ </span><span style=\"color: #0000ff; text-decoration-color: #0000ff\">elif</span> <span style=\"color: #00ffff; text-decoration-color: #00ffff\">type</span>(config) <span style=\"color: #ff00ff; text-decoration-color: #ff00ff\">in</span> <span style=\"color: #00ffff; text-decoration-color: #00ffff\">cls</span>._model_mapping.keys(): <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> <span style=\"color: #7f7f7f; text-decoration-color: #7f7f7f\">489 </span><span style=\"color: #7f7f7f; text-decoration-color: #7f7f7f\">│ │ │ </span>model_class = _get_model_class(config, <span style=\"color: #00ffff; text-decoration-color: #00ffff\">cls</span>._model_mapping) <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> <span style=\"color: #800000; text-decoration-color: #800000\">❱ </span>490 <span style=\"color: #7f7f7f; text-decoration-color: #7f7f7f\">│ │ │ </span><span style=\"color: #0000ff; text-decoration-color: #0000ff\">return</span> model_class.from_pretrained( <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> <span style=\"color: #7f7f7f; text-decoration-color: #7f7f7f\">491 </span><span style=\"color: #7f7f7f; text-decoration-color: #7f7f7f\">│ │ │ │ </span>pretrained_model_name_or_path, *model_args, config=config, **hub_kwargs, <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> <span style=\"color: #7f7f7f; text-decoration-color: #7f7f7f\">492 </span><span style=\"color: #7f7f7f; text-decoration-color: #7f7f7f\">│ │ │ </span>) <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> <span style=\"color: #7f7f7f; text-decoration-color: #7f7f7f\">493 </span><span style=\"color: #7f7f7f; text-decoration-color: #7f7f7f\">│ │ </span><span style=\"color: #0000ff; text-decoration-color: #0000ff\">raise</span> <span style=\"color: #00ffff; text-decoration-color: #00ffff\">ValueError</span>( <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> <span style=\"color: #bfbf7f; text-decoration-color: #bfbf7f\">/home/ubuntu/mambaforge/envs/dlk2/lib/python3.9/site-packages/transformers/</span><span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">modeling_utils.py</span>:<span style=\"color: #0000ff; text-decoration-color: #0000ff\">277</span> <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> <span style=\"color: #0000ff; text-decoration-color: #0000ff\">4</span> in <span style=\"color: #00ff00; text-decoration-color: #00ff00\">from_pretrained</span> <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> <span style=\"color: #7f7f7f; text-decoration-color: #7f7f7f\">2771 </span><span style=\"color: #7f7f7f; text-decoration-color: #7f7f7f\">│ │ │ │ │ </span>key: device_map[key] <span style=\"color: #0000ff; text-decoration-color: #0000ff\">for</span> key <span style=\"color: #ff00ff; text-decoration-color: #ff00ff\">in</span> device_map.keys() <span style=\"color: #0000ff; text-decoration-color: #0000ff\">if</span> key <span style=\"color: #ff00ff; text-decoration-color: #ff00ff\">not</span> <span style=\"color: #ff00ff; text-decoration-color: #ff00ff\">in</span> modu <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> <span style=\"color: #7f7f7f; text-decoration-color: #7f7f7f\">2772 </span><span style=\"color: #7f7f7f; text-decoration-color: #7f7f7f\">│ │ │ │ </span>} <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> <span style=\"color: #7f7f7f; text-decoration-color: #7f7f7f\">2773 </span><span style=\"color: #7f7f7f; text-decoration-color: #7f7f7f\">│ │ │ │ </span><span style=\"color: #0000ff; text-decoration-color: #0000ff\">if</span> <span style=\"color: #808000; text-decoration-color: #808000\">\"cpu\"</span> <span style=\"color: #ff00ff; text-decoration-color: #ff00ff\">in</span> device_map_without_lm_head.values() <span style=\"color: #ff00ff; text-decoration-color: #ff00ff\">or</span> <span style=\"color: #808000; text-decoration-color: #808000\">\"disk\"</span> <span style=\"color: #ff00ff; text-decoration-color: #ff00ff\">in</span> device_map_ <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> <span style=\"color: #800000; text-decoration-color: #800000\">❱ </span>2774 <span style=\"color: #7f7f7f; text-decoration-color: #7f7f7f\">│ │ │ │ │ </span><span style=\"color: #0000ff; text-decoration-color: #0000ff\">raise</span> <span style=\"color: #00ffff; text-decoration-color: #00ffff\">ValueError</span>( <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> <span style=\"color: #7f7f7f; text-decoration-color: #7f7f7f\">2775 </span><span style=\"color: #bfbfbf; text-decoration-color: #bfbfbf\">│ │ │ │ │ │ </span><span style=\"color: #808000; text-decoration-color: #808000\">\"\"\"</span> <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> <span style=\"color: #7f7f7f; text-decoration-color: #7f7f7f\">2776 </span><span style=\"color: #bfbf7f; text-decoration-color: #bfbf7f\">│ │ │ │ │ │ </span><span style=\"color: #808000; text-decoration-color: #808000\">Some modules are dispatched on the CPU or the disk. Make sure yo</span> <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||||
"<span style=\"color: #800000; text-decoration-color: #800000\">│</span> <span style=\"color: #7f7f7f; text-decoration-color: #7f7f7f\">2777 </span><span style=\"color: #bfbf7f; text-decoration-color: #bfbf7f\">│ │ │ │ │ │ </span><span style=\"color: #808000; text-decoration-color: #808000\">the quantized model. If you want to dispatch the model on the CP</span> <span style=\"color: #800000; text-decoration-color: #800000\">│</span>\n",
|
||||
"<span style=\"color: #800000; text-decoration-color: #800000\">╰──────────────────────────────────────────────────────────────────────────────────────────────────╯</span>\n",
|
||||
"<span style=\"color: #ff0000; text-decoration-color: #ff0000; font-weight: bold\">ValueError: </span>\n",
|
||||
" Some modules are dispatched on the CPU or the disk. Make sure you have enough GPU RAM to \n",
|
||||
"fit\n",
|
||||
" the quantized model. If you want to dispatch the model on the CPU or the disk while keeping\n",
|
||||
" these modules in <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">32</span>-bit, you need to set `<span style=\"color: #808000; text-decoration-color: #808000\">load_in_8bit_fp32_cpu_offload</span>=<span style=\"color: #00ff00; text-decoration-color: #00ff00; font-style: italic\">True</span>` and pass a \n",
|
||||
"custom\n",
|
||||
" `device_map` to `from_pretrained`. Check\n",
|
||||
" <span style=\"color: #0000ff; text-decoration-color: #0000ff; text-decoration: underline\">https://huggingface.co/docs/transformers/main/en/main_classes/quantization#offload-between-</span>\n",
|
||||
"<span style=\"color: #0000ff; text-decoration-color: #0000ff; text-decoration: underline\">cpu-and-gpu</span>\n",
|
||||
" for more details.\n",
|
||||
" \n",
|
||||
"</pre>\n"
|
||||
],
|
||||
"text/plain": [
|
||||
"\u001b[31m╭─\u001b[0m\u001b[31m──────────────────────────────\u001b[0m\u001b[31m \u001b[0m\u001b[1;31mTraceback \u001b[0m\u001b[1;2;31m(most recent call last)\u001b[0m\u001b[31m \u001b[0m\u001b[31m───────────────────────────────\u001b[0m\u001b[31m─╮\u001b[0m\n",
|
||||
"\u001b[31m│\u001b[0m in \u001b[92m<module>\u001b[0m:\u001b[94m26\u001b[0m \u001b[31m│\u001b[0m\n",
|
||||
"\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
|
||||
"\u001b[31m│\u001b[0m \u001b[2m23 \u001b[0mlora_repo = \u001b[94mNone\u001b[0m \u001b[31m│\u001b[0m\n",
|
||||
"\u001b[31m│\u001b[0m \u001b[2m24 \u001b[0m \u001b[31m│\u001b[0m\n",
|
||||
"\u001b[31m│\u001b[0m \u001b[2m25 \u001b[0mtokenizer = LlamaTokenizer.from_pretrained(model_repo) \u001b[31m│\u001b[0m\n",
|
||||
"\u001b[31m│\u001b[0m \u001b[31m❱ \u001b[0m26 model = AutoModelForCausalLM.from_pretrained(model_repo, **model_options) \u001b[31m│\u001b[0m\n",
|
||||
"\u001b[31m│\u001b[0m \u001b[2m27 \u001b[0m \u001b[31m│\u001b[0m\n",
|
||||
"\u001b[31m│\u001b[0m \u001b[2m28 \u001b[0m\u001b[94mif\u001b[0m lora_repo \u001b[95mis\u001b[0m \u001b[95mnot\u001b[0m \u001b[94mNone\u001b[0m: \u001b[31m│\u001b[0m\n",
|
||||
"\u001b[31m│\u001b[0m \u001b[2m29 \u001b[0m\u001b[2m│ \u001b[0m\u001b[2m# https://github.com/tloen/alpaca-lora/blob/main/generate.py#L40\u001b[0m \u001b[31m│\u001b[0m\n",
|
||||
"\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
|
||||
"\u001b[31m│\u001b[0m \u001b[2;33m/home/ubuntu/mambaforge/envs/dlk2/lib/python3.9/site-packages/transformers/models/auto/\u001b[0m\u001b[1;33mauto_fact\u001b[0m \u001b[31m│\u001b[0m\n",
|
||||
"\u001b[31m│\u001b[0m \u001b[1;33mory.py\u001b[0m:\u001b[94m490\u001b[0m in \u001b[92mfrom_pretrained\u001b[0m \u001b[31m│\u001b[0m\n",
|
||||
"\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
|
||||
"\u001b[31m│\u001b[0m \u001b[2m487 \u001b[0m\u001b[2m│ │ │ \u001b[0m) \u001b[31m│\u001b[0m\n",
|
||||
"\u001b[31m│\u001b[0m \u001b[2m488 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[94melif\u001b[0m \u001b[96mtype\u001b[0m(config) \u001b[95min\u001b[0m \u001b[96mcls\u001b[0m._model_mapping.keys(): \u001b[31m│\u001b[0m\n",
|
||||
"\u001b[31m│\u001b[0m \u001b[2m489 \u001b[0m\u001b[2m│ │ │ \u001b[0mmodel_class = _get_model_class(config, \u001b[96mcls\u001b[0m._model_mapping) \u001b[31m│\u001b[0m\n",
|
||||
"\u001b[31m│\u001b[0m \u001b[31m❱ \u001b[0m490 \u001b[2m│ │ │ \u001b[0m\u001b[94mreturn\u001b[0m model_class.from_pretrained( \u001b[31m│\u001b[0m\n",
|
||||
"\u001b[31m│\u001b[0m \u001b[2m491 \u001b[0m\u001b[2m│ │ │ │ \u001b[0mpretrained_model_name_or_path, *model_args, config=config, **hub_kwargs, \u001b[31m│\u001b[0m\n",
|
||||
"\u001b[31m│\u001b[0m \u001b[2m492 \u001b[0m\u001b[2m│ │ │ \u001b[0m) \u001b[31m│\u001b[0m\n",
|
||||
"\u001b[31m│\u001b[0m \u001b[2m493 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[94mraise\u001b[0m \u001b[96mValueError\u001b[0m( \u001b[31m│\u001b[0m\n",
|
||||
"\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
|
||||
"\u001b[31m│\u001b[0m \u001b[2;33m/home/ubuntu/mambaforge/envs/dlk2/lib/python3.9/site-packages/transformers/\u001b[0m\u001b[1;33mmodeling_utils.py\u001b[0m:\u001b[94m277\u001b[0m \u001b[31m│\u001b[0m\n",
|
||||
"\u001b[31m│\u001b[0m \u001b[94m4\u001b[0m in \u001b[92mfrom_pretrained\u001b[0m \u001b[31m│\u001b[0m\n",
|
||||
"\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
|
||||
"\u001b[31m│\u001b[0m \u001b[2m2771 \u001b[0m\u001b[2m│ │ │ │ │ \u001b[0mkey: device_map[key] \u001b[94mfor\u001b[0m key \u001b[95min\u001b[0m device_map.keys() \u001b[94mif\u001b[0m key \u001b[95mnot\u001b[0m \u001b[95min\u001b[0m modu \u001b[31m│\u001b[0m\n",
|
||||
"\u001b[31m│\u001b[0m \u001b[2m2772 \u001b[0m\u001b[2m│ │ │ │ \u001b[0m} \u001b[31m│\u001b[0m\n",
|
||||
"\u001b[31m│\u001b[0m \u001b[2m2773 \u001b[0m\u001b[2m│ │ │ │ \u001b[0m\u001b[94mif\u001b[0m \u001b[33m\"\u001b[0m\u001b[33mcpu\u001b[0m\u001b[33m\"\u001b[0m \u001b[95min\u001b[0m device_map_without_lm_head.values() \u001b[95mor\u001b[0m \u001b[33m\"\u001b[0m\u001b[33mdisk\u001b[0m\u001b[33m\"\u001b[0m \u001b[95min\u001b[0m device_map_ \u001b[31m│\u001b[0m\n",
|
||||
"\u001b[31m│\u001b[0m \u001b[31m❱ \u001b[0m2774 \u001b[2m│ │ │ │ │ \u001b[0m\u001b[94mraise\u001b[0m \u001b[96mValueError\u001b[0m( \u001b[31m│\u001b[0m\n",
|
||||
"\u001b[31m│\u001b[0m \u001b[2m2775 \u001b[0m\u001b[2;90m│ │ │ │ │ │ \u001b[0m\u001b[33m\"\"\"\u001b[0m \u001b[31m│\u001b[0m\n",
|
||||
"\u001b[31m│\u001b[0m \u001b[2m2776 \u001b[0m\u001b[2;33m│ │ │ │ │ │ \u001b[0m\u001b[33mSome modules are dispatched on the CPU or the disk. Make sure yo\u001b[0m \u001b[31m│\u001b[0m\n",
|
||||
"\u001b[31m│\u001b[0m \u001b[2m2777 \u001b[0m\u001b[2;33m│ │ │ │ │ │ \u001b[0m\u001b[33mthe quantized model. If you want to dispatch the model on the CP\u001b[0m \u001b[31m│\u001b[0m\n",
|
||||
"\u001b[31m╰──────────────────────────────────────────────────────────────────────────────────────────────────╯\u001b[0m\n",
|
||||
"\u001b[1;91mValueError: \u001b[0m\n",
|
||||
" Some modules are dispatched on the CPU or the disk. Make sure you have enough GPU RAM to \n",
|
||||
"fit\n",
|
||||
" the quantized model. If you want to dispatch the model on the CPU or the disk while keeping\n",
|
||||
" these modules in \u001b[1;36m32\u001b[0m-bit, you need to set `\u001b[33mload_in_8bit_fp32_cpu_offload\u001b[0m=\u001b[3;92mTrue\u001b[0m` and pass a \n",
|
||||
"custom\n",
|
||||
" `device_map` to `from_pretrained`. Check\n",
|
||||
" \u001b[4;94mhttps://huggingface.co/docs/transformers/main/en/main_classes/quantization#offload-between-\u001b[0m\n",
|
||||
"\u001b[4;94mcpu-and-gpu\u001b[0m\n",
|
||||
" for more details.\n",
|
||||
" \n"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
|
||||
+111
-858
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user