snowfly/

Llama-3-8B-QLoRA-ruozhiba

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "snowfly/Llama-3-8B-QLoRA-ruozhiba"

model = AutoModelForCausalLM.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)


text = "### Human:如何写代码? ### Assistant:"
device = "cuda:0"

inputs = tokenizer(text, return_tensors="pt").to(device)


outputs = model.generate(**inputs, max_new_tokens=50)



print(tokenizer.decode(outputs[0], skip_special_tokens=True))