Update app.py

app.py

@@ -1,36 +1,27 @@
+from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
 import torch
-from transformers import AutoTokenizer, AutoModelForCausalLM
-import gradio as gr
+from flask import Flask, render_template, request, jsonify
 
-model_name = "LeoLM/leo-mistral-chat"
+app = Flask(__name__)
 
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForCausalLM.from_pretrained(
-    model_name,
-    torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32,
-)
-model = model.to("cuda" if torch.cuda.is_available() else "cpu")
+MODEL_NAME = "ml6team/german-gpt2"
+tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
+model = AutoModelForCausalLM.from_pretrained(MODEL_NAME)
+generator = pipeline("text-generation", model=model, tokenizer=tokenizer, device=0 if torch.cuda.is_available() else -1)
 
-def chat(user_input, history=[]):
-    # Baue den Prompt auf
-    prompt = ""
-    for user, bot in history:
-        prompt += f"User: {user}\nAssistant: {bot}\n"
-    prompt += f"User: {user_input}\nAssistant:"
+@app.route("/")
+def index():
+    return render_template("index.html")
 
-    inputs = tokenizer(prompt, return_tensors="pt", truncation=True).to(model.device)
-    output = model.generate(**inputs, max_new_tokens=256, do_sample=True, top_p=0.9, temperature=0.7, pad_token_id=tokenizer.eos_token_id)
-    decoded = tokenizer.decode(output[0], skip_special_tokens=True)
-    answer = decoded.split("Assistant:")[-1].strip()
-    history.append((user_input, answer))
-    return history, history
+@app.route("/chat", methods=["POST"])
+def chat():
+    data = request.get_json()
+    user_input = data.get("message", "")
+    if not user_input:
+        return jsonify({"response": "Bitte geben Sie eine Nachricht ein."})
 
-with gr.Blocks() as demo:
-    gr.Markdown("## 🤖 Leichtgewichtiger KI-Chat auf Deutsch")
-    chatbot = gr.Chatbot()
-    msg = gr.Textbox(label="Deine Nachricht")
-    state = gr.State([])
+    output = generator(user_input, max_length=200, num_return_sequences=1, do_sample=True)[0]["generated_text"]
+    return jsonify({"response": output.strip()})
 
-    msg.submit(chat, [msg, state], [chatbot, state])
-
-demo.launch()
+if __name__ == "__main__":
+    app.run(debug=True, host="0.0.0.0", port=8080)