Update app.py

app.py

@@ -1,64 +1,63 @@
 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("HuggingFaceH4/zephyr-7b-beta")
-
-
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+import spaces
+
+# Load the tokenizer and model
+tokenizer = AutoTokenizer.from_pretrained("diabolic6045/open-llama-Instruct")
+model = AutoModelForCausalLM.from_pretrained("diabolic6045/open-llama-Instruct")
+model.eval()
+if torch.cuda.is_available():
+    model.to('cuda')
+
+@Spaces.GPU()
 def respond(
     message,
-    history: list[tuple[str, str]],
+    history,
     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,
+    # Build the conversation history
+    conversation = f"System: {system_message}\n"
+    for user_msg, bot_msg in history:
+        conversation += f"User: {user_msg}\nAssistant: {bot_msg}\n"
+    conversation += f"User: {message}\nAssistant:"
+
+    # Tokenize the input
+    inputs = tokenizer(conversation, return_tensors='pt', truncation=True, max_length=1024)
+    if torch.cuda.is_available():
+        inputs = {k: v.to('cuda') for k, v in inputs.items()}
+
+    # Generate the response
+    output = model.generate(
+        **inputs,
+        max_new_tokens=max_tokens,
+        do_sample=True,
         temperature=temperature,
         top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
+        pad_token_id=tokenizer.eos_token_id
+    )
+    response = tokenizer.decode(output[0], skip_special_tokens=True)
 
-        response += token
-        yield response
+    # Extract the assistant's reply
+    response = response[len(conversation):].strip()
+    return response
 
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
+# Create the Gradio interface with the Ocean theme
 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"),
-        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.Textbox(value="You are a friendly Chatbot.", label="System Message"),
+        gr.Slider(minimum=1, maximum=512, value=256, step=1, label="Max New Tokens"),
+        gr.Slider(minimum=0.1, maximum=1.0, value=0.7, step=0.05, label="Temperature"),
+        gr.Slider(minimum=0.1, maximum=1.0, value=0.9, step=0.05, label="Top-p (Nucleus Sampling)"),
     ],
+    title="Open Llama Chatbot",
+    description="Chat with an AI assistant powered by the Open Llama Instruct model.",
+    theme=gr.themes.Ocean(),
 )
 
-
 if __name__ == "__main__":
     demo.launch()