RichardErkhov/

Corianas_-_tiny-llama-miniguanaco-1.5T-4bits

from transformers import pipeline, AutoTokenizer, AutoModelForCausalLM

pipe = pipeline("text-generation", model="Corianas/tiny-llama-miniguanaco-1.5T")# Load model directly

tokenizer = AutoTokenizer.from_pretrained("Corianas/tiny-llama-miniguanaco-1.5T")
model = AutoModelForCausalLM.from_pretrained("Corianas/tiny-llama-miniguanaco-1.5T")

# Run text generation pipeline with our next model
prompt = "What is a large language model?"
pipe = pipeline(task="text-generation", model=model, tokenizer=tokenizer, max_length=500)
result = pipe(f"<s>{prompt}")
print(result[0]['generated_text'])