Update app.py

app.py

@@ -1,8 +1,8 @@
 from transformers import AutoTokenizer, AutoModel
 import gradio as gr
 
-tokenizer = AutoTokenizer.from_pretrained(".\\models\\chatglm-6b-int4", trust_remote_code=True, revision="")
-model = AutoModel.from_pretrained(".\\models\\chatglm-6b-int4", trust_remote_code=True, revision="").half().cuda().cpu()
+# tokenizer = AutoTokenizer.from_pretrained(".\\models\\chatglm-6b-int4", trust_remote_code=True, revision="")
+# model = AutoModel.from_pretrained(".\\models\\chatglm-6b-int4", trust_remote_code=True, revision="").half().cuda().cpu()
 
 
 # from transformers import AutoTokenizer, AutoModel
@@ -12,9 +12,9 @@ model = AutoModel.from_pretrained(".\\models\\chatglm-6b-int4", trust_remote_cod
 
 
 # kernel_file = "./models/chatglm-6b-int4/quantization_kernels.so"
-# tokenizer = AutoTokenizer.from_pretrained("./models/chatglm-6b-int4", trust_remote_code=True, revision="")
+tokenizer = AutoTokenizer.from_pretrained("./models/chatglm-6b-int4", trust_remote_code=True, revision="")
 # model = AutoModel.from_pretrained("./models/chatglm-6b-int4", trust_remote_code=True, revision="").half().cuda()
-# model = AutoModel.from_pretrained("./models/chatglm-6b-int4", trust_remote_code=True, revision="").half()
+model = AutoModel.from_pretrained("./models/chatglm-6b-int4", trust_remote_code=True, revision="").float()