auto git

config.json

@@ -8,7 +8,6 @@
     "AutoModel": "modeling_chatglm.ChatGLMForConditionalGeneration",
     "AutoModelForSeq2SeqLM": "modeling_chatglm.ChatGLMForConditionalGeneration"
   },
-  "device": "cuda",
   "bos_token_id": 130004,
   "eos_token_id": 130005,
   "mask_token_id": 130000,

demo_pipeline.py

@@ -1,4 +1,4 @@
 
 from transformers import pipeline
-nlp = pipeline('text2text-generation',model ='.\\',trust_remote_code=True)
+nlp = pipeline('text2text-generation',model ='THUDM/chatglm-6b',trust_remote_code=True)
 # response = nlp

load_model.py

@@ -1,9 +1,10 @@
-from transformers import AutoTokenizer, AutoModel
+from transformers import AutoTokenizer, AutoModel,pipeline
 
 #
-tokenizer = AutoTokenizer.from_pretrained(".\\", trust_remote_code=True)
-# model = AutoModel.from_pretrained(".\\", trust_remote_code=True).float()
-model = AutoModel.from_pretrained(".\\", trust_remote_code=True)
-model = model.eval()
-response, history = model.chat(tokenizer, "你好", history=[])
-print("response:", response)
+# tokenizer = AutoTokenizer.from_pretrained(".\\", trust_remote_code=True)
+# # model = AutoModel.from_pretrained(".\\", trust_remote_code=True).float()
+# model = AutoModel.from_pretrained(".\\", trust_remote_code=True)
+# model = model.eval()
+# response, history = model.chat(tokenizer, "你好", history=[])
+# print("response:", response)
+npl = pipeline('')