Update app.py

app.py

@@ -1,48 +1,70 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
 
+import os
+import spaces
+from transformers import GemmaTokenizer, AutoModelForCausalLM
+from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
+from threading import Thread
 
+HF_TOKEN = os.environ.get("HF_TOKEN", None)
 """
 For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
 """
-client = InferenceClient("LLMproj1/mypersona-llama3-8b")
+tokenizer = AutoTokenizer.from_pretrained("LLMproj1/mypersona-llama3-8b")
+model = AutoModelForCausalLM.from_pretrained("LLMproj1/mypersona-llama3-8b", device_map="auto")
+terminators = [
+    tokenizer.eos_token_id,
+    tokenizer.convert_tokens_to_ids("<|eot_id|>")
+]
 
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+@spaces.GPU(duration=120)
+def chat_mistral7b_v0dot3(message: str, 
+              history: list, 
+              temperature: float, 
+              max_new_tokens: int
+             ) -> str:
+    """
+    Generate a streaming response using the mistralai/Mistral-7B-Instruct-v0.3 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})
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+    input_ids = tokenizer.apply_chat_template(conversation, return_tensors="pt").to(model.device)
+    
+    streamer = TextIteratorStreamer(tokenizer, timeout=10.0, skip_prompt=True, skip_special_tokens=True)
 
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
+    generate_kwargs = dict(
+        input_ids= input_ids,
+        streamer=streamer,
+        max_new_tokens=max_new_tokens,
+        do_sample=True,
         temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
+        eos_token_id=terminators,
+    )
+    # This will enforce greedy generation (do_sample=False) when the temperature is passed 0, avoiding the crash.             
+    if temperature == 0:
+        generate_kwargs['do_sample'] = False
+        
+    t = Thread(target=model.generate, kwargs=generate_kwargs)
+    t.start()
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
+    outputs = []
+    for text in streamer:
+        outputs.append(text)
+        #print(outputs)
+        yield "".join(outputs)
+        
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[