from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer, pipeline
from transformers import AutoTokenizer  # Add this import

tokenizer = AutoTokenizer.from_pretrained("your_model_name")  # Add this line
streamer = TextStreamer(tokenizer, skip_prompt=True)
pipe = pipeline(
    "text-generation",
    model=model_fintuned,
    tokenizer=tokenizer,
    max_length=2048,
    temperature=0.6,
    pad_token_id=tokenizer.eos_token_id,
    top_p=0.95,
    repetition_penalty=1.2,
    device=device,
    streamer=streamer
)
pipe(prompts[0])

inputs = tokenizer(prompts[0], return_tensors="pt").to(device)
streamer = TextStreamer(tokenizer, skip_prompt=True)
_ = model_fintuned.generate(**inputs, streamer=streamer, pad_token_id=tokenizer.eos_token_id, max_length=248, temperature=0.8, top_p=0.8,
                        repetition_penalty=1.25)