Upload 3 files

app.py

@@ -1,21 +1,25 @@
 from flask import Flask, render_template, request, jsonify
+from getans import get_response
 
 app = Flask(__name__)
 
 # Store chat history
 chat_history = []
 
+
 @app.route('/')
 def index():
     return render_template('index.html', chat_history=chat_history)
 
+
 @app.route('/send_message', methods=['POST'])
 def send_message():
     user_message = request.form['message']
     # Here you can process the user message and generate a response
-    bot_response = f"Echo: {user_message}"
+    bot_response = get_response(user_message, max_new_tokens=100)
     chat_history.append({'user': user_message, 'bot': bot_response})
     return jsonify(chat_history=chat_history)
 
+
 if __name__ == '__main__':
     app.run(debug=True)

getans.py

@@ -0,0 +1,14 @@
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+
+tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-2-7b-chat-hf")
+model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-2-7b-chat-hf")
+
+
+def get_response(prompt, max_new_tokens=50):
+    inputs = tokenizer(prompt, return_tensors="pt")
+    outputs = model.generate(**inputs, max_new_tokens=max_new_tokens, temperature=0.0001, do_sample=True)
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)  # Use indexing instead of calling
+    return response

requirements.txt

@@ -1,2 +1,4 @@
-Flask~=3.0.3
-gunicorn~=22.0.0
+Flask~=3.0.3
+gunicorn~=22.0.0
+torch
+transformers