Update app.py

app.py

@@ -1,33 +1,37 @@
+import gradio as gr
 from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
 import torch
-from flask import Flask, request, jsonify
 
-app = Flask(_name_)
+# Load free model from Hugging Face (like Mistral or Mixtral)
+model_name = "mistralai/Mistral-7B-Instruct-v0.1"
 
-# Load powerful model
-model_id = "HuggingFaceH4/zephyr-7b-beta"
-tokenizer = AutoTokenizer.from_pretrained(model_id)
-model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto")
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    torch_dtype=torch.float16,
+    device_map="auto"
+)
 
-# Pipeline
-generator = pipeline("text-generation", model=model, tokenizer=tokenizer)
+pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)
 
-@app.route("/generate", methods=["POST"])
-def generate():
-    input_data = request.json
-    prompt = input_data.get("prompt", "")
+def generate_answer(question):
+    prompt = f"[INST] {question} [/INST]"
+    output = pipe(prompt, max_new_tokens=500, do_sample=True, temperature=0.7)[0]['generated_text']
     
-    result = generator(
-        prompt,
-        max_new_tokens=500,  # Longer response
-        temperature=0.7,
-        top_k=50,
-        top_p=0.95,
-        repetition_penalty=1.2,
-        do_sample=True,
-    )
-    
-    return jsonify({"response": result[0]['generated_text']})
+    # Cut only the answer part (after the [/INST] token)
+    if "[/INST]" in output:
+        answer = output.split("[/INST]")[-1].strip()
+    else:
+        answer = output
+
+    return answer
+
+iface = gr.Interface(
+    fn=generate_answer,
+    inputs=gr.Textbox(lines=2, placeholder="Ask any question..."),
+    outputs="text",
+    title="MentorMind AI Q&A",
+    description="Ask anything and get a detailed human-like answer!"
+)
 
-if _name_ == "_main_":
-    app.run(host="0.0.0.0", port=7860)
+iface.launch()