|
@@ -7,25 +7,25 @@ import torch
|
|
|
|
|
|
|
|
|
class ChatGLM_LLM(LLM):
|
|
|
-
|
|
|
+
|
|
|
tokenizer: AutoTokenizer = None
|
|
|
model: AutoModelForCausalLM = None
|
|
|
|
|
|
def __init__(self, model_path: str):
|
|
|
-
|
|
|
-
|
|
|
+
|
|
|
+
|
|
|
super().__init__()
|
|
|
- print("正在从本地加载模型...")
|
|
|
+ print("锟斤拷锟节从憋拷锟截硷拷锟斤拷模锟斤拷...")
|
|
|
self.tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
|
|
|
self.model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True).to(torch.bfloat16).cuda(
|
|
|
device=1)
|
|
|
self.model = self.model.eval()
|
|
|
- print("完成本地模型的加载")
|
|
|
+ print("锟斤拷杀锟斤拷锟侥o拷偷募锟斤拷锟�")
|
|
|
|
|
|
def _call(self, prompt: str, stop: Optional[List[str]] = None,
|
|
|
run_manager: Optional[CallbackManagerForLLMRun] = None,
|
|
|
**kwargs: Any):
|
|
|
-
|
|
|
+
|
|
|
response, history = self.model.chat(self.tokenizer, prompt, history=[], do_sample=False)
|
|
|
return response
|
|
|
|