updates to memory

app.py

@@ -69,41 +69,41 @@ tokenizer.padding_side = 'left'
 peft_config = PeftConfig.from_pretrained("Tonic/mistralmed", token="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")
 peft_model = MistralForCausalLM.from_pretrained("mistralai/Mistral-7B-v0.1", trust_remote_code=True)
 peft_model = PeftModel.from_pretrained(peft_model, "Tonic/mistralmed", token="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")
-
+#Remove the memory function
 class ChatBot:
     def __init__(self):
         self.history = []
-
+#
     def predict(self, user_input, system_prompt="You are an expert medical analyst:"):
         # Combine user input and system prompt
         formatted_input = f"<s>[INST]{system_prompt} {user_input}[/INST]"
-
+#
         # Encode user input
         user_input_ids = tokenizer.encode(formatted_input, return_tensors="pt")
-
-        # Concatenate the user input with chat history
-        if len(self.history) > 0:
-            chat_history_ids = torch.cat([self.history, user_input_ids], dim=-1)
-        else:
-            chat_history_ids = user_input_ids
-
+#
+#        # Concatenate the user input with chat history
+#        if len(self.history) > 0:
+#            chat_history_ids = torch.cat([self.history, user_input_ids], dim=-1)
+#        else:
+#            chat_history_ids = user_input_ids
+#
         # Generate a response using the PEFT model
-        response = peft_model.generate(input_ids=chat_history_ids, max_length=512, pad_token_id=tokenizer.eos_token_id)
-
-        # Update chat history
-        self.history = chat_history_ids
-
+#        response = peft_model.generate(input_ids=chat_history_ids, max_length=512, pad_token_id=tokenizer.eos_token_id)
+         response = peft_model.generate(input_ids, max_length=512, pad_token_id=tokenizer.eos_token_id)
+#        # Update chat history
+#        self.history = chat_history_ids
+#
         # Decode and return the response
-        response_text = tokenizer.decode(response[0], skip_special_tokens=True)
-        return response_text
-
+       response_text = tokenizer.decode(response[0], skip_special_tokens=True)
+       return response_text
+#
 bot = ChatBot()
-
+#
 title = "👋🏻토닉의 미스트랄메드 채팅에 오신 것을 환영합니다🚀👋🏻Welcome to Tonic's MistralMed Chat🚀"
 description = "이 공간을 사용하여 현재 모델을 테스트할 수 있습니다. [(Tonic/MistralMed)](https://huggingface.co/Tonic/MistralMed) 또는 이 공간을 복제하고 로컬 또는 🤗HuggingFace에서 사용할 수 있습니다. [Discord에서 함께 만들기 위해 Discord에 가입하십시오](https://discord.gg/VqTxc76K3u). You can use this Space to test out the current model [(Tonic/MistralMed)](https://huggingface.co/Tonic/MistralMed) or duplicate this Space and use it locally or on 🤗HuggingFace. [Join me on Discord to build together](https://discord.gg/VqTxc76K3u)."
 examples = [["[Question:] What is the proper treatment for buccal herpes?", "You are a medicine and public health expert, you will recieve a question, answer the question and complete answer"]]
 
-iface = gr.Interface(
+ iface = gr.Interface(
     fn=bot.predict,
     title=title,
     description=description,