🚀 LongWriter-glm4-9b
LongWriter-glm4-9b是一款基於大語言模型開發的文本生成工具,它基於glm-4-9b訓練而來,具備一次性生成10000字以上文本的能力,為長文本創作提供了強大支持。
🚀 快速開始
環境要求
與glm-4-9b-chat的環境要求相同(transformers>=4.43.0
)。
模型部署示例
基礎用法
以下是一個簡單的模型部署示例代碼:
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
tokenizer = AutoTokenizer.from_pretrained("THUDM/LongWriter-glm4-9b", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("THUDM/LongWriter-glm4-9b", torch_dtype=torch.bfloat16, trust_remote_code=True, device_map="auto")
model = model.eval()
query = "Write a 10000-word China travel guide"
response, history = model.chat(tokenizer, query, history=[], max_new_tokens=32768, temperature=0.5)
print(response)
高級用法
你還可以使用vllm來部署模型,它可以在一分鐘內完成10000字以上的文本生成。以下是示例代碼:
from vllm import LLM, SamplingParams
model = LLM(
model= "THUDM/LongWriter-glm4-9b",
dtype="auto",
trust_remote_code=True,
tensor_parallel_size=1,
max_model_len=32768,
gpu_memory_utilization=1,
)
tokenizer = model.get_tokenizer()
stop_token_ids = [tokenizer.eos_token_id, tokenizer.get_command("<|user|>"), tokenizer.get_command("<|observation|>")]
generation_params = SamplingParams(
temperature=0.5,
top_p=0.8,
top_k=50,
max_tokens=32768,
repetition_penalty=1,
stop_token_ids=stop_token_ids
)
query = "Write a 10000-word China travel guide"
input_ids = tokenizer.build_chat_input(query, history=[], role='user').input_ids[0].tolist()
outputs = model.generate(
sampling_params=generation_params,
prompt_token_ids=[input_ids],
)
output = outputs[0]
print(output.outputs[0].text)
📄 許可證
本項目遵循glm-4-9b License。
📚 詳細文檔
引用信息
如果您覺得我們的工作有幫助,請考慮引用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}
}
相關鏈接