LongWriter-llama3.1-8b

🤗 [LongWriter 数据集] • 💻 [GitHub 仓库] • 📃 [LongWriter 论文]

LongWriter-llama3.1-8b 是基于 Meta-Llama-3.1-8B 训练的，能够一次性生成 10,000+ 个单词。

环境：transformers>=4.43.0

请遵循提示模板（系统提示可选）：<<SYS>>\n{系统提示}\n<</SYS>>\n\n[INST]{查询1}[/INST]{响应1}[INST]{查询2}[/INST]{响应2}...

模型部署的一个简单示例：

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)

你也可以使用 vllm 来部署模型，它能在短短一分钟内生成超过 10,000 个单词。以下是一个示例代码：

model = LLM(
    model= "THUDM/LongWriter-llama3.1-8b",
    dtype="auto",
    trust_remote_code=True,
    tensor_parallel_size=1,
    max_model_len=32768,
    gpu_memory_utilization=0.5,
)
tokenizer = model.get_tokenizer()
generation_params = SamplingParams(
    temperature=0.5,
    top_p=0.8,
    top_k=50,
    max_tokens=32768,
    repetition_penalty=1,
)
query = "Write a 10000-word China travel guide"
prompt = f"[INST]{query}[/INST]"
input_ids = tokenizer(prompt, truncation=False, return_tensors="pt").input_ids[0].tolist()
outputs = model.generate(
    sampling_params=generation_params,
    prompt_token_ids=[input_ids],
)
output = outputs[0]
print(output.outputs[0].text)

许可协议：Llama-3.1 许可协议

引用

如果您发现我们的工作有所帮助，请考虑引用 LongWriter：

@article{bai2024longwriter,
  title={LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs}, 
  author={Yushi Bai and Jiajie Zhang and Xin Lv and Linzhi Zheng and Siqi Zhu and Lei Hou and Yuxiao Dong and Jie Tang and Juanzi Li},
  journal={arXiv preprint arXiv:2408.07055},
  year={2024}
}

当然，我能够帮助您翻译文本内容。不过，我需要您提供需要翻译的原文，这样才能进行翻译。请提供您希望我翻译的文本。