Update app.py

app.py

@@ -1,64 +1,26 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
+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 fine-tuned TinyLLaMA model from Hugging Face
+model_name = "your-username/tinyllama-qlora-support-bot"  # 🔁 Replace with your actual HF repo name
 
+# Use FP16 if supported, fallback to CPU
+device = "cuda" if torch.cuda.is_available() else "cpu"
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16 if device=="cuda" else torch.float32).to(device)
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+# Pipeline for response generation
+generator = pipeline("text-generation", model=model, tokenizer=tokenizer, device=0 if device=="cuda" else -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)",
-        ),
-    ],
-)
+def chatbot(message, history=[]):
+    prompt = f"### Instruction:\n{message}\n\n### Response:\n"
+    output = generator(prompt, max_new_tokens=256, do_sample=True, temperature=0.7)
+    response = output[0]["generated_text"].split("### Response:\n")[-1].strip()
+    return response
 
+interface = gr.ChatInterface(fn=chatbot, title="🦙 LLaMA Support Chatbot", theme="soft")
 
 if __name__ == "__main__":
-    demo.launch()
+    interface.launch()