Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Does AutoAWQ support to quantize GLM-4-9B-Chat and ChatGLM3-6B two models? #642

Open
shawn9977 opened this issue Nov 7, 2024 · 0 comments

Comments

@shawn9977
Copy link


TypeError Traceback (most recent call last)
Cell In[2], line 2
1 # 加载模型
----> 2 model = AutoAWQForCausalLM.from_pretrained(model_name_or_path, trust_remote_code=True)
3 tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, trust_remote_code=True)

File ~/miniforge3/envs/peft/lib/python3.10/site-packages/awq/models/auto.py:55, in AutoAWQForCausalLM.from_pretrained(self, model_path, trust_remote_code, safetensors, device_map, **model_init_kwargs)
46 @classmethod
47 def from_pretrained(
48 self,
(...)
53 **model_init_kwargs,
54 ) -> BaseAWQForCausalLM:
---> 55 model_type = check_and_get_model_type(
56 model_path, trust_remote_code, **model_init_kwargs
57 )
59 return AWQ_CAUSAL_LM_MODEL_MAP[model_type].from_pretrained(
60 model_path,
61 model_type,
(...)
65 **model_init_kwargs,
66 )

File ~/miniforge3/envs/peft/lib/python3.10/site-packages/awq/models/auto.py:34, in check_and_get_model_type(model_dir, trust_remote_code, **model_init_kwargs)
...
---> 34 raise TypeError(f"{config.model_type} isn't supported yet.")
35 model_type = config.model_type
36 return model_type

TypeError: chatglm isn't supported yet.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant