Update app.py

app.py

@@ -1,64 +1,76 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+from transformers import AutoModelForCausalLM, AutoTokenizer
+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
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+# Load the model and tokenizer
+model_name = "TheDrummer/Gemmasutra-Mini-2B-v1"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name)
 
+# Ensure model runs on CPU (default for Hugging Face Spaces free tier)
+device = torch.device("cpu")
+model.to(device)
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+# Chatbot function
+def chat_with_model(user_input, history):
+    # Format history and input into a single prompt
+    if history is None:
+        history = []
+    
+    # Build conversation context
+    prompt = ""
+    for h in history:
+        prompt += f"User: {h[0]}\nBot: {h[1]}\n"
+    prompt += f"User: {user_input}\nBot: "
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    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"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
+    # Tokenize input
+    inputs = tokenizer(prompt, return_tensors="pt").to(device)
+    
+    # Generate response
+    outputs = model.generate(
+        **inputs,
+        max_new_tokens=150,  # Limit response length
+        do_sample=True,      # Enable sampling for varied responses
+        temperature=0.7,     # Control creativity
+        top_p=0.9,           # Nucleus sampling
+        pad_token_id=tokenizer.eos_token_id  # Handle padding
+    )
+    
+    # Decode response
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    
+    # Extract just the bot's reply (after the last "Bot: ")
+    bot_response = response.split("Bot: ")[-1].strip()
+    
+    # Update history
+    history.append((user_input, bot_response))
+    return bot_response, history
 
+# Gradio Interface
+with gr.Blocks(title="Grok-like Chatbot") as iface:
+    gr.Markdown("## Chat with Gemmasutra-Mini-2B-v1")
+    chatbot = gr.Chatbot(label="Conversation")
+    msg = gr.Textbox(label="Your Message", placeholder="Type here...")
+    submit_btn = gr.Button("Send")
+    
+    # State to maintain conversation history
+    state = gr.State(value=[])
+    
+    def submit_message(user_input, history):
+        response, updated_history = chat_with_model(user_input, history)
+        return response, updated_history, updated_history, ""
+    
+    # Connect button and enter key to submit
+    submit_btn.click(
+        fn=submit_message,
+        inputs=[msg, state],
+        outputs=[msg, state, chatbot, msg]  # Clear input after submission
+    )
+    msg.submit(
+        fn=submit_message,
+        inputs=[msg, state],
+        outputs=[msg, state, chatbot, msg]
+    )
 
 if __name__ == "__main__":
-    demo.launch()
+    iface.launch()