Update app.py

app.py

@@ -1,64 +1,60 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-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("diabolic6045/ELN-Llama-1B-base")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_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]})
-
-    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
-"""
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
+# Initialize model and tokenizer
+tokenizer = AutoTokenizer.from_pretrained("diabolic6045/ELN-Llama-1B-base")
+model = AutoModelForCausalLM.from_pretrained("diabolic6045/ELN-Llama-1B-base")
+
+def generate_response(message, history):
+    # Format the conversation history
+        
+    print("here")
+    conversation = ""
+    for h in history:
+        conversation += f"User: {h[0]}\nAssistant: {h[1]}\n"
+    conversation += f"User: {message}\nAssistant:"
+    
+    # Tokenize input
+    inputs = tokenizer(conversation, return_tensors="pt", truncation=True, max_length=512)
+    
+    # Generate response
+    with torch.no_grad():
+        outputs = model.generate(
+            inputs["input_ids"],
+            max_length=200,
+            temperature=0.7,
+            do_sample=True,
+            pad_token_id=tokenizer.eos_token_id,
+            num_return_sequences=1,
+        )
+    
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    # Extract only the assistant's response
+    response = response.split("Assistant:")[-1].strip()
+    
+    return response
+
+# Create the Gradio interface
 demo = gr.ChatInterface(
-    respond,
+    fn=generate_response,
+    type="messages",
+    title="LLaMA Chatbot",
+    description="Chat with the ELN-Llama-1B model. Ask questions or have a conversation!",
+    examples=[
+        "What is artificial intelligence?",
+        "Write a short poem about nature.",
+        "Explain quantum computing in simple terms.",
+    ],
+    cache_examples=True,
     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)",
-        ),
+        gr.Slider(minimum=0.1, maximum=1.0, value=0.7, label="Temperature"),
+        gr.Slider(minimum=50, maximum=500, value=200, step=50, label="Max Length"),
     ],
+    retry_btn="Regenerate",
+    undo_btn="Undo Last",
+    clear_btn="Clear",
 )
 
-
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch(share=True)