from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
tokenizer = AutoTokenizer.from_pretrained("THUDM/LongWriter-llama3.1-8b", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("THUDM/LongWriter-llama3.1-8b", torch_dtype=torch.bfloat16, trust_remote_code=True, device_map="auto")
model = model.eval()
query = "Write a 10000-word China travel guide"
prompt = f"[INST]{query}[/INST]"
input = tokenizer(prompt, truncation=False, return_tensors="pt").to(device)
context_length = input.input_ids.shape[-1]
output = model.generate(
    **input,
    max_new_tokens=32768,
    num_beams=1,
    do_sample=True,
    temperature=0.5,
)[0]
response = tokenizer.decode(output[context_length:], skip_special_tokens=True)
print(response)

License: Llama-3.1 License

Citation

If you find our work useful, please consider citing LongWriter:

KnutJaegersberg/LongWriter-8b-exl-8.0bpw

LongWriter-llama3.1-8b

Citation

KnutJaegersberg/
LongWriter-8b-exl-8.0bpw