LongWriter
LongWriter enables generation of texts longer than 10,000 words using long-context LLMs
GraphCanon updated 1d · GitHub synced 1d
Decision brief
LongWriter specializes in exceeding the text generation limit to over 10,000 words using long-context LLMs for Python-based development.
Good fit when
- For projects requiring texts longer than 10,000 words with fine-tuned llm models
- When working on tasks that demand high-context retention across very large text outputs
Avoid when
- Avoid for short-form content generation where LLM context is less relevant
- Not ideal when the requirement is to maintain conciseness in output texts
Observed Jul 16, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Dormant (425d since push)
- As of 1d
- Provenance
- Not a fork · Organization account
- As of 1d
- Security (OSV)
- No lockfile
- As of 1mo
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
pip install LongWriterSimilar tools
Same-category neighbours. No typed graph edges are catalogued for this tool yet.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
[ICLR 2025] LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs, implemented in Python with focus on fine-tuning and llm functionalities
Capability facts
- Languages
- python
Source: github.language · Aug 24, 2026
Categories
Compatibility
Sourced claims from the README excerpt - not unsourced marketing copy.
Source: README excerpt (regex_v1, Aug 24, 2026)
```python from transformers import AutoTokenizer, AutoModelForCausalLMSource link
Tags
README
⚙️ LongWriter Deployment
Environmental Setup:
We recommend using transformers>=4.43.0 to successfully deploy our models.
We open-source two models: LongWriter-glm4-9b and LongWriter-llama3.1-8b, trained based on GLM-4-9B and Meta-Llama-3.1-8B, respectively. These two models point to the "LongWriter-9B-DPO" and "LongWriter-8B" models in our paper. Try the model:
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)
You may deploy your own LongWriter chatbot (like the one we show in the teasor video) by running
CUDA_VISIBLE_DEVICES=0 python trans_web_demo.py
Alternatively, you can deploy the model with vllm, which allows generating 10,000+ words within a minute! See the code example in vllm_inference.py.
For agents
This page has a .md twin and JSON over the API.