Update main.py

main.py

@@ -10,15 +10,20 @@ client = InferenceClient("mistralai/Mixtral-8x7B-Instruct-v0.1")
 
 class Item(BaseModel):
     prompt: str
+    history: list
     system_prompt: str
     temperature: float = 0.0
     max_new_tokens: int = 1048
     top_p: float = 0.15
     repetition_penalty: float = 1.0
 
-def format_prompt(example):
-    text = f"### Instruction: {example['input']}\n ### Response: {example['output']}"
-    return text
+def format_prompt(message, history):
+    prompt = "<s>"
+    for user_prompt, bot_response in history:
+        prompt += f"[INST] {user_prompt} [/INST]"
+        prompt += f" {bot_response}</s> "
+    prompt += f"[INST] {message} [/INST]"
+    return prompt
 
 def generate(item: Item):
     temperature = float(item.temperature)
@@ -35,7 +40,7 @@ def generate(item: Item):
         seed=42,
     )
 
-    formatted_prompt = format_prompt(f"{item.system_prompt}, {item.prompt}")
+    formatted_prompt = format_prompt(f"{item.system_prompt}, {item.prompt}", item.history)
     stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
     output = ""