Gaze/ChatGLM2-6B
1
1
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

add multiple GPUs usage comments for python files

Browse Source
This commit is contained in:
Qin Jianxiang 2023-06-27 13:20:46 +08:00
parent 3fb52912a9
commit 5916e3feeb
3 changed files with 12 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
api.py
View File

@ -52,5 +52,9 @@ async def create_item(request: Request):
if __name__ == '__main__': if __name__ == '__main__':
tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True) tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True)
model = AutoModel.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True).cuda() model = AutoModel.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True).cuda()
# 多显卡支持，使用下面三行代替上面两行，将num_gpus改为你实际的显卡数量
# model_path = "THUDM/chatglm2-6b"
# tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
# model = load_model_on_gpus(model_path, num_gpus=2)
model.eval() model.eval()
uvicorn.run(app, host='0.0.0.0', port=8000, workers=1) uvicorn.run(app, host='0.0.0.0', port=8000, workers=1)

4
openai_api.py
View File

@ -158,6 +158,10 @@ async def predict(query: str, history: List[List[str]], model_id: str):
if __name__ == "__main__": if __name__ == "__main__":
tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True) tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True)
model = AutoModel.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True).cuda() model = AutoModel.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True).cuda()
# 多显卡支持，使用下面三行代替上面两行，将num_gpus改为你实际的显卡数量
# model_path = "THUDM/chatglm2-6b"
# tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
# model = load_model_on_gpus(model_path, num_gpus=2)
model.eval() model.eval()
uvicorn.run(app, host='0.0.0.0', port=8000, workers=1) uvicorn.run(app, host='0.0.0.0', port=8000, workers=1)

4
web_demo2.py
View File

@ -14,6 +14,10 @@ st.set_page_config(
def get_model(): def get_model():
tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True) tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True)
model = AutoModel.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True).cuda() model = AutoModel.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True).cuda()
# 多显卡支持，使用下面三行代替上面两行，将num_gpus改为你实际的显卡数量
# model_path = "THUDM/chatglm2-6b"
# tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
# model = load_model_on_gpus(model_path, num_gpus=2)
model = model.eval() model = model.eval()
return tokenizer, model return tokenizer, model