weiweiw
/
Langchain-Chatchat
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

chatglm init twice (#313)

This commit is contained in:
Tyler Luan 2023-05-11 11:31:15 +08:00 committed by GitHub
parent 2987c9cd52
commit 31655339f0
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
models/chatglm_llm.py
View File

@ -141,16 +141,16 @@ class ChatGLM(LLM):
else:
from accelerate import dispatch_model
model = AutoModel.from_pretrained(model_name_or_path, trust_remote_code=True,
config=model_config, **kwargs)
# model = AutoModel.from_pretrained(model_name_or_path, trust_remote_code=True,
# config=model_config, **kwargs)
if LLM_LORA_PATH and use_lora:
from peft import PeftModel
model = PeftModel.from_pretrained(model, LLM_LORA_PATH)
model = PeftModel.from_pretrained(self.model, LLM_LORA_PATH)
# 可传入device_map自定义每张卡的部署情况
if device_map is None:
device_map = auto_configure_device_map(num_gpus)
self.model = dispatch_model(model.half(), device_map=device_map)
self.model = dispatch_model(self.model.half(), device_map=device_map)
else:
self.model = self.model.float().to(llm_device)