Update app.py

app.py

@@ -1,22 +1,19 @@
-from transformers import AutoTokenizer, AutoModelForCausalLM
-import torch
+from llama_cpp import Llama
 from telegram import Update
 from telegram.ext import Application, CommandHandler, MessageHandler, filters, CallbackContext
 
-# ✅ Model Name
-model_name = "TheBloke/Pygmalion-13B-SuperHOT-8K-GPTQ"
+# ✅ Hugging Face Model Path
+model_path = "TheBloke/Pygmalion-13B-SuperHOT-8K-GPTQ"
 
 # ✅ Load Model
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto", torch_dtype=torch.float16)
+model = Llama.from_pretrained(model_path, model_file="model.gguf", n_ctx=4096)
 
 # ✅ Telegram Bot Token
 TELEGRAM_BOT_TOKEN = "7881901341:AAEaE5gndeORmCuyzSwOyf2ELFLXHneCpiw"
 
 def chat(prompt):
-    inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
-    output = model.generate(**inputs, max_new_tokens=200, do_sample=True, temperature=0.7, top_p=0.9)
-    return tokenizer.decode(output[0], skip_special_tokens=True)
+    output = model(prompt, max_tokens=200, temperature=0.7, top_p=0.9)
+    return output["choices"][0]["text"]
 
 # ✅ Telegram Commands
 async def start(update: Update, context: CallbackContext) -> None: