lm-sys / lm-sys/FastChat

WizardCoder 33B is not supported?

Open
#2,917 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
39.5k
Forks
4.8k
PR merge metrics
No merged PRs in 30d

Description

```
2024-01-12 14:57:53 | INFO | model_worker | Loading the model ['WizardCoder-33B-V1.1'] on worker 21fbf439 ...
2024-01-12 14:57:53 | ERROR | stderr | Traceback (most recent call last):
2024-01-12 14:57:53 | ERROR | stderr | File "/root/miniconda3/envs/wizardcoder/lib/python3.10/site-packages/fastchat/model/model_adapter.py", line 74, in load_model
2024-01-12 14:57:53 | ERROR | stderr | tokenizer = AutoTokenizer.from_pretrained(
2024-01-12 14:57:53 | ERROR | stderr | File "/root/miniconda3/envs/wizardcoder/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py", line 787, in from_pretrained
2024-01-12 14:57:53 | ERROR | stderr | return tokenizer_class.from_pretrained(pretrained_model_name_or_path, *inputs, **kwargs)
2024-01-12 14:57:53 | ERROR | stderr | File "/root/miniconda3/envs/wizardcoder/lib/python3.10/site-packages/transformers/tokenization_utils_base.py", line 2028, in from_pretrained
2024-01-12 14:57:53 | ERROR | stderr | return cls._from_pretrained(
2024-01-12 14:57:53 | ERROR | stderr | File "/root/miniconda3/envs/wizardcoder/lib/python3.10/site-packages/transformers/tokenization_utils_base.py", line 2260, in _from_pretrained
2024-01-12 14:57:53 | ERROR | stderr | tokenizer = cls(*init_inputs, **init_kwargs)
2024-01-12 14:57:53 | ERROR | stderr | File "/root/miniconda3/envs/wizardcoder/lib/python3.10/site-packages/transformers/models/llama/tokenization_llama.py", line 178, in __init__
2024-01-12 14:57:53 | ERROR | stderr | self.sp_model = self.get_spm_processor(kwargs.pop("from_slow", False))
2024-01-12 14:57:53 | ERROR | stderr | File "/root/miniconda3/envs/wizardcoder/lib/python3.10/site-packages/transformers/models/llama/tokenization_llama.py", line 203, in get_spm_processor
2024-01-12 14:57:53 | ERROR | stderr | tokenizer.Load(self.vocab_file)
2024-01-12 14:57:53 | ERROR | stderr | File "/root/miniconda3/envs/wizardcoder/lib/python3.10/site-packages/sentencepiece/__init__.py", line 905, in Load
2024-01-12 14:57:53 | ERROR | stderr | return self.LoadFromFile(model_file)
2024-01-12 14:57:53 | ERROR | stderr | File "/root/miniconda3/envs/wizardcoder/lib/python3.10/site-packages/sentencepiece/__init__.py", line 310, in LoadFromFile
2024-01-12 14:57:53 | ERROR | stderr | return _sentencepiece.SentencePieceProcessor_LoadFromFile(self, arg)
2024-01-12 14:57:53 | ERROR | stderr | TypeError: not a string
2024-01-12 14:57:53 | ERROR | stderr |
2024-01-12 14:57:53 | ERROR | stderr | During handling of the above exception, another exception occurred:
2024-01-12 14:57:53 | ERROR | stderr |
2024-01-12 14:57:53 | ERROR | stderr | Traceback (most recent call last):
2024-01-12 14:57:53 | ERROR | stderr | File "/root/miniconda3/envs/wizardcoder/lib/python3.10/runpy.py", line 196, in _run_module_as_main
2024-01-12 14:57:53 | ERROR | stderr | return _run_code(code, main_globals, None,
2024-01-12 14:57:53 | ERROR | stderr | File "/root/miniconda3/envs/wizardcoder/lib/python3.10/runpy.py", line 86, in _run_code
2024-01-12 14:57:53 | ERROR | stderr | exec(code, run_globals)
2024-01-12 14:57:53 | ERROR | stderr | File "/root/miniconda3/envs/wizardcoder/lib/python3.10/site-packages/fastchat/serve/model_worker.py", line 369, in
2024-01-12 14:57:53 | ERROR | stderr | args, worker = create_model_worker()
2024-01-12 14:57:53 | ERROR | stderr | File "/root/miniconda3/envs/wizardcoder/lib/python3.10/site-packages/fastchat/serve/model_worker.py", line 341, in create_model_worker
2024-01-12 14:57:53 | ERROR | stderr | worker = ModelWorker(
2024-01-12 14:57:53 | ERROR | stderr | File "/root/miniconda3/envs/wizardcoder/lib/python3.10/site-packages/fastchat/serve/model_worker.py", line 77, in __init__
2024-01-12 14:57:53 | ERROR | stderr | self.model, self.tokenizer = load_model(
2024-01-12 14:57:53 | ERROR | stderr | File "/root/miniconda3/envs/wizardcoder/lib/python3.10/site-packages/fastchat/model/model_adapter.py", line 323, in load_model
2024-01-12 14:57:53 | ERROR | stderr | model, tokenizer = adapter.load_model(model_path, kwargs)
2024-01-12 14:57:53 | ERROR | stderr | File "/root/miniconda3/envs/wizardcoder/lib/python3.10/site-packages/fastchat/model/model_adapter.py", line 81, in load_model
2024-01-12 14:57:53 | ERROR | stderr | tokenizer = AutoTokenizer.from_pretrained(
2024-01-12 14:57:53 | ERROR | stderr | File "/root/miniconda3/envs/wizardcoder/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py", line 787, in from_pretrained
2024-01-12 14:57:53 | ERROR | stderr | return tokenizer_class.from_pretrained(pretrained_model_name_or_path, *inputs, **kwargs)
2024-01-12 14:57:53 | ERROR | stderr | File "/root/miniconda3/envs/wizardcoder/lib/python3.10/site-packages/transformers/tokenization_utils_base.py", line 2028, in from_pretrained
2024-01-12 14:57:53 | ERROR | stderr | return cls._from_pretrained(
2024-01-12 14:57:53 | ERROR | stderr | File "/root/miniconda3/envs/wizardcoder/lib/python3.10/site-packages/transformers/tokenization_utils_base.py", line 2260, in _from_pretrained
2024-01-12 14:57:53 | ERROR | stderr | tokenizer = cls(*init_inputs, **init_kwargs)
2024-01-12 14:57:53 | ERROR | stderr | File "/root/miniconda3/envs/wizardcoder/lib/python3.10/site-packages/transformers/models/llama/tokenization_llama.py", line 178, in __init__
2024-01-12 14:57:53 | ERROR | stderr | self.sp_model = self.get_spm_processor(kwargs.pop("from_slow", False))
2024-01-12 14:57:53 | ERROR | stderr | File "/root/miniconda3/envs/wizardcoder/lib/python3.10/site-packages/transformers/models/llama/tokenization_llama.py", line 203, in get_spm_processor
2024-01-12 14:57:53 | ERROR | stderr | tokenizer.Load(self.vocab_file)
2024-01-12 14:57:53 | ERROR | stderr | File "/root/miniconda3/envs/wizardcoder/lib/python3.10/site-packages/sentencepiece/__init__.py", line 905, in Load
2024-01-12 14:57:53 | ERROR | stderr | return self.LoadFromFile(model_file)
2024-01-12 14:57:53 | ERROR | stderr | File "/root/miniconda3/envs/wizardcoder/lib/python3.10/site-packages/sentencepiece/__init__.py", line 310, in LoadFromFile
2024-01-12 14:57:53 | ERROR | stderr | return _sentencepiece.SentencePieceProcessor_LoadFromFile(self, arg)
2024-01-12 14:57:53 | ERROR | stderr | TypeError: not a string

```

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reading fastchat/model/model_adapter.py around load_model and fastchat/serve/model_worker.py around create_model_worker and ModelWorker. Reproduce loading WizardCoder-33B-V1.1 and trace the tokenizer failure; done means the model worker loads this model without the reported TypeError.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Bug
Difficulty
3/5
Estimated time
1-2 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.