Liger
Collection
6 items • Updated • 3
How to use from
vLLMInstall from pip and serve model
# Install vLLM from pip:
pip install vllm# Start the vLLM server:
vllm serve "linear-moe-hub/Liger-GLA-8B"# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "linear-moe-hub/Liger-GLA-8B",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'Use Docker
docker model run hf.co/linear-moe-hub/Liger-GLA-8BQuick Links
Liger-GLA-8B
[📂 GitHub] [📜 Liger] [📑 Paper]
We introduce Liger-GLA-8B, a gated linear recurrent model linearized from Transformer-based LLM.
Our Liger framework is compatible with various linear recurrent models with gating structures:
| Model Name | Base Model | Linear Structure | HF Link |
|---|---|---|---|
| Liger-GLA-8B | Llama-3-8B | GLA | 🤗 link |
| Liger-GSA-8B | Llama-3-8B | GSA | 🤗 link |
Citation
If you find this repo useful, please cite and star our work:
@article{lan2025liger,
title={Liger: Linearizing Large Language Models to Gated Recurrent Structures},
author={Lan, Disen and Sun, Weigao and Hu, Jiaxi and Du, Jusen and Cheng, Yu},
journal={arXiv preprint arXiv:2503.01496},
year={2025}
}
- Downloads last month
- -
Collection including linear-moe-hub/Liger-GLA-8B
Papers for linear-moe-hub/Liger-GLA-8B
Liger: Linearizing Large Language Models to Gated Recurrent Structures
Paper • 2503.01496 • Published • 18
Gated Slot Attention for Efficient Linear-Time Sequence Modeling
Paper • 2409.07146 • Published • 20
Gated Linear Attention Transformers with Hardware-Efficient Training
Paper • 2312.06635 • Published • 9
# Gated model: Login with a HF token with gated access permission hf auth login