app.py

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# ✅ Model name update karo
model_name = "TheBloke/Pygmalion-13B-SuperHOT-8K-GPTQ"

# ✅ Tokenizer Load karo
tokenizer = AutoTokenizer.from_pretrained(model_name)

# ✅ Model Load karo (Automatic Device Selection)
model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto", torch_dtype=torch.float16)

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)

# ✅ Test Chat
while True:
    user_input = input("You: ")
    if user_input.lower() in ["exit", "quit"]:
        break
    response = chat(user_input)
    print("AI:", response)