from transformers import AutoModelForCausalLM, AutoTokenizer, pineline

model = AutoModelForCausalLM.from_pretrained(
          "lifeofcoding/mastermax-llama-7b",
          load_in_4bit=True)
tokenizer = AutoTokenizer.from_pretrained("lifeofcoding/mastermax-llama-7b", trust_remote_code=True)

# Generate text using the pipeline
pipe = pipeline(task="text-generation",
                model=model,
                tokenizer=tokenizer,
                max_length=200)

result = pipe(f"<s>[INST] {prompt} [/INST]")
generated_text = result[0]['generated_text']