Should there be tokenizer files in the repo?
#2
by
Yhyu13
- opened
I pulled this repo the local directory and try to load with --model-path by setting a local path. But Hugging face transformer still want to download the tokenizer confi from online which causes some error
│ /home/hangyu5/Documents/Git-repoMy/AIResearchVault/repo/LLM/BLOOM/LLMZoo/llmzoo/deploy/webapp/in │
│ ference.py:235 in chat_loop │
│ │
│ 232 │ │ debug: bool, │
│ 233 ): │
│ 234 │ # Model │
│ ❱ 235 │ model, tokenizer = load_model( │
│ 236 │ │ model_path, device, num_gpus, max_gpu_memory, load_8bit, load_4bit, debug │
│ 237 │ ) │
│ 238 │
│ │
│ /home/hangyu5/Documents/Git-repoMy/AIResearchVault/repo/LLM/BLOOM/LLMZoo/llmzoo/deploy/webapp/in │
│ ference.py:94 in load_model │
│ │
│ 91 │ │ tokenizer = AutoTokenizer.from_pretrained(model_path, use_fast=True) │
│ 92 │ │ model = AutoModelForCausalLM.from_pretrained(model_path, low_cpu_mem_usage=True, │
│ 93 │ else: │
│ ❱ 94 │ │ tokenizer = AutoTokenizer.from_pretrained(model_path, use_fast=True) │
│ 95 │ │ model = AutoModelForCausalLM.from_pretrained(model_path, low_cpu_mem_usage=True, │
│ 96 │ │
│ 97 │ if load_8bit: │
│ │
│ /home/hangyu5/anaconda3/envs/pheonix/lib/python3.10/site-packages/transformers/models/auto/token │
│ ization_auto.py:642 in from_pretrained │
│ │
│ 639 │ │ │ return tokenizer_class.from_pretrained(pretrained_model_name_or_path, *input │
│ 640 │ │ │
│ 641 │ │ # Next, let's try to use the tokenizer_config file to get the tokenizer class. │
│ ❱ 642 │ │ tokenizer_config = get_tokenizer_config(pretrained_model_name_or_path, **kwargs) │
│ 643 │ │ if "_commit_hash" in tokenizer_config: │
│ 644 │ │ │ kwargs["_commit_hash"] = tokenizer_config["_commit_hash"] │
│ 645 │ │ config_tokenizer_class = tokenizer_config.get("tokenizer_class") │
│ │
│ /home/hangyu5/anaconda3/envs/pheonix/lib/python3.10/site-packages/transformers/models/auto/token │
│ ization_auto.py:486 in get_tokenizer_config │
│ │
│ 483 │ tokenizer_config = get_tokenizer_config("tokenizer-test") │
│ 484 │ ```""" │
│ 485 │ commit_hash = kwargs.get("_commit_hash", None) │
│ ❱ 486 │ resolved_config_file = cached_file( │
│ 487 │ │ pretrained_model_name_or_path, │
│ 488 │ │ TOKENIZER_CONFIG_FILE, │
│ 489 │ │ cache_dir=cache_dir, │
│ │
│ /home/hangyu5/anaconda3/envs/pheonix/lib/python3.10/site-packages/transformers/utils/hub.py:409 │
│ in cached_file │
│ │
│ 406 │ user_agent = http_user_agent(user_agent) │
│ 407 │ try: │
│ 408 │ │ # Load from URL or cache if already cached │
│ ❱ 409 │ │ resolved_file = hf_hub_download( │
│ 410 │ │ │ path_or_repo_id, │
│ 411 │ │ │ filename, │
│ 412 │ │ │ subfolder=None if len(subfolder) == 0 else subfolder, │
│ │
│ /home/hangyu5/anaconda3/envs/pheonix/lib/python3.10/site-packages/huggingface_hub/utils/_validat │
│ ors.py:112 in _inner_fn │
│ │
│ 109 │ │ │ kwargs.items(), # Kwargs values │
│ 110 │ │ ): │
│ 111 │ │ │ if arg_name in ["repo_id", "from_id", "to_id"]: │
│ ❱ 112 │ │ │ │ validate_repo_id(arg_value) │
│ 113 │ │ │ │
│ 114 │ │ │ elif arg_name == "token" and arg_value is not None: │
│ 115 │ │ │ │ has_token = True │
│ │
│ /home/hangyu5/anaconda3/envs/pheonix/lib/python3.10/site-packages/huggingface_hub/utils/_validat │
│ ors.py:160 in validate_repo_id │
│ │
│ 157 │ │ raise HFValidationError(f"Repo id must be a string, not {type(repo_id)}: '{repo_ │
│ 158 │ │
│ 159 │ if repo_id.count("/") > 1: │
│ ❱ 160 │ │ raise HFValidationError( │
│ 161 │ │ │ "Repo id must be in the form 'repo_name' or 'namespace/repo_name':" │
│ 162 │ │ │ f" '{repo_id}'. Use `repo_type` argument if needed." │
│ 163 │ │ ) │
╰─────────────────────────────────────────────────────────────────
Yes, we should include tokenizer files. And you could reuse the tokenizer files from FreedomIntelligence/phoenix-inst-chat-7b at the moment.
Thanks for pointing that out.
GeneZC
changed discussion status to
closed
GeneZC
changed discussion status to
open
And we have found a bug in our code, please use the updated version of our repo.