Upload folder using huggingface_hub

.ipynb_checkpoints/web_demo-checkpoint.py

@@ -3,8 +3,12 @@ import gradio as gr
 import mdtex2html
 from utils import load_model_on_gpus
 
-tokenizer = AutoTokenizer.from_pretrained(r"/mnt/workspace/chatglm-6b", trust_remote_code=True)
-model = AutoModel.from_pretrained(r"/mnt/workspace/chatglm-6b", trust_remote_code=True).half().cuda()
+
+tokenizer = AutoTokenizer.from_pretrained(r"THUDM/chatglm2-6b", trust_remote_code=True)
+model = AutoModel.from_pretrained(r"THUDM/chatglm2-6b", trust_remote_code=True).half().cuda()
+
+# tokenizer = AutoTokenizer.from_pretrained(r"/mnt/workspace/chatglm-6b", trust_remote_code=True)
+# model = AutoModel.from_pretrained(r"/mnt/workspace/chatglm-6b", trust_remote_code=True).half().cuda()
 # 多显卡支持，使用下面两行代替上面一行，将num_gpus改为你实际的显卡数量
 # from utils import load_model_on_gpus
 # model = load_model_on_gpus("THUDM/chatglm2-6b", num_gpus=2)

web_demo.py

@@ -3,8 +3,12 @@ import gradio as gr
 import mdtex2html
 from utils import load_model_on_gpus
 
-tokenizer = AutoTokenizer.from_pretrained(r"/mnt/workspace/chatglm-6b", trust_remote_code=True)
-model = AutoModel.from_pretrained(r"/mnt/workspace/chatglm-6b", trust_remote_code=True).half().cuda()
+
+tokenizer = AutoTokenizer.from_pretrained(r"THUDM/chatglm2-6b", trust_remote_code=True)
+model = AutoModel.from_pretrained(r"THUDM/chatglm2-6b", trust_remote_code=True).half().cuda()
+
+# tokenizer = AutoTokenizer.from_pretrained(r"/mnt/workspace/chatglm-6b", trust_remote_code=True)
+# model = AutoModel.from_pretrained(r"/mnt/workspace/chatglm-6b", trust_remote_code=True).half().cuda()
 # 多显卡支持，使用下面两行代替上面一行，将num_gpus改为你实际的显卡数量
 # from utils import load_model_on_gpus
 # model = load_model_on_gpus("THUDM/chatglm2-6b", num_gpus=2)