Update app.py

app.py

@@ -1,64 +1,61 @@
 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")
-
-
-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
-"""
-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)",
-        ),
-    ],
-)
-
-
-if __name__ == "__main__":
-    demo.launch()
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+# Replace with your actual model ID
+model_id = "alphaoumardev/Llama3-8B-noryu-instruct"
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id)
+model.eval()
+
+# If you're using GPU on HF Spaces with GPU enabled
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+model.to(device)
+
+def chat(user_input, history=[]):
+    # Add user input to the history
+    history.append({"role": "user", "content": user_input})
+
+    # Format prompt (adjust as needed depending on your training)
+    prompt = ""
+    for turn in history:
+        role = turn["role"]
+        content = turn["content"]
+        prompt += f"{role}: {content}\n"
+    prompt += "assistant:"
+
+    # Tokenize and generate
+    inputs = tokenizer(prompt, return_tensors="pt").to(device)
+    with torch.no_grad():
+        outputs = model.generate(
+            **inputs,
+            max_new_tokens=200,
+            do_sample=True,
+            temperature=0.7,
+            top_p=0.9,
+            pad_token_id=tokenizer.eos_token_id
+        )
+
+    output_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    
+    # Extract just the assistant's reply
+    assistant_reply = output_text.split("assistant:")[-1].strip()
+    history.append({"role": "assistant", "content": assistant_reply})
+
+    # Return response and updated history for Gradio
+    chat_history = [(h["content"], history[i + 1]["content"]) for i, h in enumerate(history[:-1]) if h["role"] == "user"]
+    return chat_history, history
+
+# Set up Gradio ChatInterface
+with gr.Blocks() as demo:
+    chatbot = gr.Chatbot()
+    state = gr.State([])  # for storing history
+    txt = gr.Textbox(show_label=False, placeholder="Type your message...")
+
+    def user_submit(user_message, history):
+        return chat(user_message, history)
+
+    txt.submit(user_submit, [txt, state], [chatbot, state])
+    
+demo.launch()