希望支持llama-2-7B的base模型 #27
Assignees
Comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
{{ message }}
Uh oh!
There was an error while loading. Please reload this page.
转换llama-2-7B的base模型，type选择Llama-2-7b-chat-ms时报错：
Traceback (most recent call last): File "llm_export.py", line 1187, in <module> llm_exporter = llm_models[model_type](args) File "llm_export.py", line 815, in __init__ super().__init__(args) File "llm_export.py", line 102, in __init__ self.load_model(args.path) File "llm_export.py", line 819, in load_model model_path, trust_remote_code=True) File "/home/env/anaconda3/envs/nio/lib/python3.7/site-packages/transformers/models/auto/tokenization_auto.py", line 635, in from_pretrained pretrained_model_name_or_path, trust_remote_code=trust_remote_code, **kwargs File "/home/env/anaconda3/envs/nio/lib/python3.7/site-packages/transformers/models/auto/configuration_auto.py", line 917, in from_pretrained config_class = CONFIG_MAPPING[config_dict["model_type"]] File "/home/env/anaconda3/envs/nio/lib/python3.7/site-packages/transformers/models/auto/configuration_auto.py", line 623, in __getitem__ raise KeyError(key) KeyError: 'llama'The text was updated successfully, but these errors were encountered: