Update app.py

app.py

@@ -48,6 +48,18 @@ h1 {
 }
 """
 
+
+import json
+
+
+import json
+
+def str_to_json(str_obj):
+    json_obj = json.loads(str_obj)
+    return json_obj
+
+
+
 # Load the tokenizer and model
 tokenizer = AutoTokenizer.from_pretrained("HumanLLMs/Human-Like-LLama3-8B-Instruct")
 model = AutoModelForCausalLM.from_pretrained("HumanLLMs/Human-Like-LLama3-8B-Instruct", device_map="auto")  # to("cuda:0") 
@@ -62,20 +74,12 @@ def chat_llama3_8b(message: str,
               temperature: float, 
               max_new_tokens: int
              ) -> str:
-    """
-    Generate a streaming response using the llama3-8b model.
-    Args:
-        message (str): The input message.
-        history (list): The conversation history used by ChatInterface.
-        temperature (float): The temperature for generating the response.
-        max_new_tokens (int): The maximum number of new tokens to generate.
-    Returns:
-        str: The generated response.
-    """
-    conversation = []
-    for user, assistant in history:
-        conversation.extend([{"role": "user", "content": user}, {"role": "assistant", "content": assistant}])
-    conversation.append({"role": "user", "content": message})
+
+    x = str_to_json(str(message)
+    conversation = x['messages']
+    # for user, assistant in history:
+    #     conversation.extend([{"role": "user", "content": user}, {"role": "assistant", "content": assistant}])
+    # conversation.append({"role": "user", "content": message})
 
     input_ids = tokenizer.apply_chat_template(conversation, return_tensors="pt").to(model.device)