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

small change of comment about multiple GPUs support

Browse Source
This commit is contained in:
Qin Jianxiang 2023-06-26 10:37:38 +08:00
parent 08ffab941f
commit a3ba2275ed
2 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
cli_demo.py
View File

@ -7,7 +7,7 @@ from utils import load_model_on_gpus
tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True)
model = AutoModel.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True, device='cuda')
# 多显卡支持，注释掉下面三行，将num_gpus改为你实际的显卡数量
# 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)

2
web_demo.py
View File

@ -4,7 +4,7 @@ import mdtex2html
tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True)
model = AutoModel.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True, device='cuda')
# 多显卡支持，注释掉下面三行，将num_gpus改为你实际的显卡数量
# 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)