Update app.py

app.py

@@ -1,11 +1,33 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
 
-"""
-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
-"""
-# Initialize the inference client with the model repo
-client = InferenceClient("cognitivecomputations/dolphin-2_6-phi-2")
+# Replace 'your_huggingface_token' with your actual Hugging Face access token
+access_token = os.getenv('token')
+
+# Initialize the tokenizer and model with the Hugging Face access token
+tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b-it", use_auth_token=access_token)
+model = AutoModelForCausalLM.from_pretrained(
+    "google/gemma-2b-it",
+    torch_dtype=torch.bfloat16,
+    use_auth_token=access_token
+)
+model.eval()  # Set the model to evaluation mode
+
+# Initialize the inference client (if needed for other API-based tasks)
+client = InferenceClient(token=access_token)
+
+def conversation_predict(input_text):
+    """Generate a response for single-turn input using the model."""
+    # Tokenize the input text
+    input_ids = tokenizer(input_text, return_tensors="pt").input_ids
+
+    # Generate a response with the model
+    outputs = model.generate(input_ids, max_new_tokens=2048)
+
+    # Decode and return the generated response
+    return tokenizer.decode(outputs[0], skip_special_tokens=True)
 
 def respond(
     message: str,
@@ -15,7 +37,7 @@ def respond(
     temperature: float,
     top_p: float,
 ):
-    """Generate a response for the chatbot using the InferenceClient."""
+    """Generate a response for a multi-turn chat conversation."""
     # Prepare the messages in the correct format for the API
     messages = [{"role": "system", "content": system_message}]
 
@@ -30,23 +52,20 @@ def respond(
     response = ""
 
     # Stream response tokens from the chat completion API
-    for message in client.chat_completion(
+    for message_chunk in client.chat_completion(
         messages=messages,
         max_tokens=max_tokens,
         stream=True,
         temperature=temperature,
         top_p=top_p,
     ):
-        token = message["choices"][0]["delta"].get("content", "")
+        token = message_chunk["choices"][0]["delta"].get("content", "")
         response += token
         yield response
 
-"""
-For information on how to customize the ChatInterface, peruse the Gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-
+# Create a Gradio ChatInterface demo
 demo = gr.ChatInterface(
-    respond,
+    fn=respond,
     additional_inputs=[
         gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
         gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),