File size: 10,395 Bytes
2459f54 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 |
/home/floriadmin/miniforge3/envs/mlc/bin/python -m mlc_llm gen_config ../dist/models/gorilla-openfunctions-v2 --quantization q8f32_1 --conv-template gorilla --output /tmp/tmpfb6fqbz7
[2024-03-18 21:03:38] INFO auto_config.py:115: [92mFound[0m model configuration: ../dist/models/gorilla-openfunctions-v2/config.json
[2024-03-18 21:03:38] INFO auto_config.py:153: [92mFound[0m model type: [1mllama[0m. Use `--model-type` to override.
[2024-03-18 21:03:38] INFO llama_model.py:52: [1mcontext_window_size[0m not found in config.json. Falling back to [1mmax_position_embeddings[0m (4096)
[2024-03-18 21:03:38] INFO llama_model.py:72: [1mprefill_chunk_size[0m defaults to [1mcontext_window_size[0m (4096)
[2024-03-18 21:03:38] INFO config.py:106: Overriding [1mmax_batch_size[0m from 1 to 80
[2024-03-18 21:03:38] INFO gen_config.py:133: [generation_config.json] Setting [1mbos_token_id[0m: 100000
[2024-03-18 21:03:38] INFO gen_config.py:133: [generation_config.json] Setting [1meos_token_id[0m: 100015
[2024-03-18 21:03:38] INFO gen_config.py:147: [91mNot found[0m tokenizer config: ../dist/models/gorilla-openfunctions-v2/tokenizer.model
[2024-03-18 21:03:38] INFO gen_config.py:145: [92mFound[0m tokenizer config: ../dist/models/gorilla-openfunctions-v2/tokenizer.json. Copying to [1m/tmp/tmpfb6fqbz7/tokenizer.json[0m
[2024-03-18 21:03:38] INFO gen_config.py:147: [91mNot found[0m tokenizer config: ../dist/models/gorilla-openfunctions-v2/vocab.json
[2024-03-18 21:03:38] INFO gen_config.py:147: [91mNot found[0m tokenizer config: ../dist/models/gorilla-openfunctions-v2/merges.txt
[2024-03-18 21:03:38] INFO gen_config.py:147: [91mNot found[0m tokenizer config: ../dist/models/gorilla-openfunctions-v2/added_tokens.json
[2024-03-18 21:03:38] INFO gen_config.py:145: [92mFound[0m tokenizer config: ../dist/models/gorilla-openfunctions-v2/tokenizer_config.json. Copying to [1m/tmp/tmpfb6fqbz7/tokenizer_config.json[0m
[2024-03-18 21:03:38] INFO gen_config.py:75: [System default] Setting [1mpad_token_id[0m: 0
[2024-03-18 21:03:38] INFO gen_config.py:75: [System default] Setting [1mtemperature[0m: 0.7
[2024-03-18 21:03:38] INFO gen_config.py:75: [System default] Setting [1mpresence_penalty[0m: 0.0
[2024-03-18 21:03:38] INFO gen_config.py:75: [System default] Setting [1mfrequency_penalty[0m: 0.0
[2024-03-18 21:03:38] INFO gen_config.py:75: [System default] Setting [1mrepetition_penalty[0m: 1.0
[2024-03-18 21:03:38] INFO gen_config.py:75: [System default] Setting [1mtop_p[0m: 0.95
[2024-03-18 21:03:38] INFO gen_config.py:75: [System default] Setting [1mmean_gen_len[0m: 128
[2024-03-18 21:03:38] INFO gen_config.py:75: [System default] Setting [1mmax_gen_len[0m: 512
[2024-03-18 21:03:38] INFO gen_config.py:75: [System default] Setting [1mshift_fill_factor[0m: 0.3
[2024-03-18 21:03:38] INFO gen_config.py:198: Dumping configuration file to: [1m/tmp/tmpfb6fqbz7/mlc-chat-config.json[0m
/home/floriadmin/miniforge3/envs/mlc/bin/python -m mlc_llm convert_weight ../dist/models/gorilla-openfunctions-v2 --quantization q8f32_1 --source-format auto --output /tmp/tmpfb6fqbz7
[2024-03-18 21:03:39] INFO auto_config.py:115: [92mFound[0m model configuration: ../dist/models/gorilla-openfunctions-v2/config.json
[2024-03-18 21:03:39] INFO auto_device.py:76: [92mFound[0m device: cuda:0
[2024-03-18 21:03:39] INFO auto_device.py:76: [92mFound[0m device: cuda:1
[2024-03-18 21:03:39] INFO auto_device.py:76: [92mFound[0m device: cuda:2
[2024-03-18 21:03:39] INFO auto_device.py:76: [92mFound[0m device: cuda:3
[2024-03-18 21:03:39] INFO auto_device.py:76: [92mFound[0m device: cuda:4
[2024-03-18 21:03:39] INFO auto_device.py:76: [92mFound[0m device: cuda:5
[2024-03-18 21:03:39] INFO auto_device.py:76: [92mFound[0m device: cuda:6
[2024-03-18 21:03:39] INFO auto_device.py:76: [92mFound[0m device: cuda:7
[2024-03-18 21:03:39] INFO auto_device.py:76: [92mFound[0m device: cuda:8
[2024-03-18 21:03:39] INFO auto_device.py:76: [92mFound[0m device: cuda:9
[2024-03-18 21:03:40] INFO auto_device.py:85: [91mNot found[0m device: rocm:0
[2024-03-18 21:03:41] INFO auto_device.py:85: [91mNot found[0m device: metal:0
[2024-03-18 21:03:44] INFO auto_device.py:76: [92mFound[0m device: vulkan:0
[2024-03-18 21:03:44] INFO auto_device.py:76: [92mFound[0m device: vulkan:1
[2024-03-18 21:03:44] INFO auto_device.py:76: [92mFound[0m device: vulkan:2
[2024-03-18 21:03:44] INFO auto_device.py:76: [92mFound[0m device: vulkan:3
[2024-03-18 21:03:44] INFO auto_device.py:76: [92mFound[0m device: vulkan:4
[2024-03-18 21:03:44] INFO auto_device.py:76: [92mFound[0m device: vulkan:5
[2024-03-18 21:03:44] INFO auto_device.py:76: [92mFound[0m device: vulkan:6
[2024-03-18 21:03:44] INFO auto_device.py:76: [92mFound[0m device: vulkan:7
[2024-03-18 21:03:44] INFO auto_device.py:76: [92mFound[0m device: vulkan:8
[2024-03-18 21:03:44] INFO auto_device.py:76: [92mFound[0m device: vulkan:9
[2024-03-18 21:03:44] INFO auto_device.py:76: [92mFound[0m device: vulkan:10
[2024-03-18 21:03:45] INFO auto_device.py:85: [91mNot found[0m device: opencl:0
[2024-03-18 21:03:45] INFO auto_device.py:33: Using device: [1mcuda:0[0m
[2024-03-18 21:03:45] INFO auto_weight.py:70: Finding weights in: ../dist/models/gorilla-openfunctions-v2
[2024-03-18 21:03:45] INFO auto_weight.py:120: [92mFound[0m source weight format: huggingface-torch. Source configuration: ../dist/models/gorilla-openfunctions-v2/pytorch_model.bin.index.json
[2024-03-18 21:03:45] INFO auto_weight.py:143: [92mFound[0m source weight format: huggingface-safetensor. Source configuration: ../dist/models/gorilla-openfunctions-v2/model.safetensors.index.json
[2024-03-18 21:03:45] INFO auto_weight.py:106: Using source weight configuration: [1m../dist/models/gorilla-openfunctions-v2/pytorch_model.bin.index.json[0m. Use `--source` to override.
[2024-03-18 21:03:45] INFO auto_weight.py:110: Using source weight format: [1mhuggingface-torch[0m. Use `--source-format` to override.
[2024-03-18 21:03:45] INFO auto_config.py:153: [92mFound[0m model type: [1mllama[0m. Use `--model-type` to override.
[2024-03-18 21:03:45] INFO llama_model.py:52: [1mcontext_window_size[0m not found in config.json. Falling back to [1mmax_position_embeddings[0m (4096)
[2024-03-18 21:03:45] INFO llama_model.py:72: [1mprefill_chunk_size[0m defaults to [1mcontext_window_size[0m (4096)
[1mWeight conversion with arguments:[0m
[1m--config[0m ../dist/models/gorilla-openfunctions-v2/config.json
[1m--quantization[0m GroupQuantize(name='q8f32_1', kind='group-quant', group_size=32, quantize_dtype='int8', storage_dtype='uint32', model_dtype='float32', linear_weight_layout='NK', quantize_embedding=True, quantize_final_fc=True, num_elem_per_storage=4, num_storage_per_group=8, max_int_value=127)
[1m--model-type[0m llama
[1m--device[0m cuda:0
[1m--source[0m ../dist/models/gorilla-openfunctions-v2/pytorch_model.bin.index.json
[1m--source-format[0m huggingface-torch
[1m--output[0m /tmp/tmpfb6fqbz7
Start storing to cache /tmp/tmpfb6fqbz7
0%| | 0/183 [00:00<?, ?it/s]
[2024-03-18 21:03:47] INFO huggingface_loader.py:182: Loading HF parameters from: ../dist/models/gorilla-openfunctions-v2/pytorch_model-00002-of-00002.bin
0%| | 0/183 [00:00<?, ?it/s]
0%| | 0/183 [00:00<?, ?it/s]
Traceback (most recent call last):
File "<frozen runpy>", line 198, in _run_module_as_main
File "<frozen runpy>", line 88, in _run_code
File "/home/floriadmin/mlc-llm/python/mlc_llm/__main__.py", line 47, in <module>
main()
File "/home/floriadmin/mlc-llm/python/mlc_llm/__main__.py", line 28, in main
cli.main(sys.argv[2:])
File "/home/floriadmin/mlc-llm/python/mlc_llm/cli/convert_weight.py", line 87, in main
convert_weight(
File "/home/floriadmin/mlc-llm/python/mlc_llm/interface/convert_weight.py", line 182, in convert_weight
_convert_args(args)
File "/home/floriadmin/mlc-llm/python/mlc_llm/interface/convert_weight.py", line 146, in _convert_args
tvmjs.dump_ndarray_cache(
File "/home/floriadmin/miniforge3/envs/mlc/lib/python3.11/site-packages/tvm/contrib/tvmjs.py", line 210, in dump_ndarray_cache
for k, origin_v in param_generator:
File "/home/floriadmin/mlc-llm/python/mlc_llm/interface/convert_weight.py", line 130, in _param_generator
for name, param in loader.load(device=args.device, preshard_funcs=preshard_funcs):
File "/home/floriadmin/mlc-llm/python/mlc_llm/loader/huggingface_loader.py", line 117, in load
param = self._load_mlc_param(mlc_name, device=device)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/floriadmin/mlc-llm/python/mlc_llm/loader/huggingface_loader.py", line 147, in _load_mlc_param
self._load_file(path)
File "/home/floriadmin/mlc-llm/python/mlc_llm/loader/huggingface_loader.py", line 186, in _load_file
for name, param in load_func(path):
File "/home/floriadmin/mlc-llm/python/mlc_llm/loader/utils.py", line 42, in load_torch_shard
for name, param in torch.load(path, map_location=torch.device("cpu")).items():
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/floriadmin/miniforge3/envs/mlc/lib/python3.11/site-packages/torch/serialization.py", line 998, in load
with _open_file_like(f, 'rb') as opened_file:
^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/floriadmin/miniforge3/envs/mlc/lib/python3.11/site-packages/torch/serialization.py", line 445, in _open_file_like
return _open_file(name_or_buffer, mode)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/floriadmin/miniforge3/envs/mlc/lib/python3.11/site-packages/torch/serialization.py", line 426, in __init__
super().__init__(open(name, mode))
^^^^^^^^^^^^^^^^
FileNotFoundError: [Errno 2] No such file or directory: '../dist/models/gorilla-openfunctions-v2/pytorch_model-00002-of-00002.bin'
|