Update app.py

app.py

@@ -1,42 +1,64 @@
-from flask import Flask, request, jsonify
-from transformers import AutoTokenizer, AutoModelForCausalLM
-import torch
+import gradio as gr
+from huggingface_hub import InferenceClient
 
-# Initialize the Flask app
-app = Flask(__name__)
+"""
+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("Futuresony/future_ai_12_10_2024.gguf")
 
-# Load the model and tokenizer
-MODEL_PATH = "Futuresony/future_ai_12_10_2024.gguf"  # Replace with your Hugging Face model name or local path
-device = "cuda" if torch.cuda.is_available() else "cpu"
 
-# Load adapter-based model
-print("Loading model...")
-tokenizer = AutoTokenizer.from_pretrained(MODEL_PATH, config="tokenizer_config.json")
+def respond(
+    message,
+    history: list[tuple[str, str]],
+    system_message,
+    max_tokens,
+    temperature,
+    top_p,
+):
+    messages = [{"role": "system", "content": system_message}]
 
-model = AutoModelForCausalLM.from_pretrained(MODEL_PATH, torch_dtype=torch.float16 if device == "cuda" else None)
-model.to(device)
-print("Model loaded successfully.")
+    for val in history:
+        if val[0]:
+            messages.append({"role": "user", "content": val[0]})
+        if val[1]:
+            messages.append({"role": "assistant", "content": val[1]})
 
-@app.route("/generate", methods=["POST"])
-def generate_text():
-    try:
-        # Extract input from JSON request
-        data = request.json
-        prompt = data.get("prompt", "")
-        max_length = data.get("max_length", 100)
+    messages.append({"role": "user", "content": message})
 
-        if not prompt:
-            return jsonify({"error": "Prompt is required"}), 400
+    response = ""
 
-        # Generate text using the model
-        inputs = tokenizer(prompt, return_tensors="pt").to(device)
-        outputs = model.generate(**inputs, max_length=max_length)
-        generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    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)",
+        ),
+    ],
+)
 
-        return jsonify({"generated_text": generated_text})
-    except Exception as e:
-        return jsonify({"error": str(e)}), 500
 
 if __name__ == "__main__":
-    app.run(debug=True, host="0.0.0.0", port=5000)
-    
+    demo.launch()