Downloads · 30 days
0
lsg_public
JH-C-k/lsg_public
lsg_public is a machine learning model from JH-C-k. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Layer-wise Sink Gating (LSG) gate checkpoints for "When Sinks Help or Hurt: Unified Framework for Attention Sink in Large Vision-Language Models" (arXiv:2604.03316). All checkpoints are gate-only (nonloratrainables.bi…
Access
Public
Updated Aug 5, 2026
Repo size
3.9 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin3.9 MB · 100%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Jul 26, 2026
- Updated
- Aug 5, 2026
- SHA
- 9f644cc3
Model card
From the Hugging Face model README
LSG checkpoints — When Sinks Help or Hurt (ECCV 2026 Oral, Spotlight)
Layer-wise Sink Gating (LSG) gate checkpoints for
"When Sinks Help or Hurt: Unified Framework for Attention Sink in Large Vision-Language Models"
(arXiv:2604.03316). All checkpoints are
gate-only (non_lora_trainables.bin, well under 3 MB each); backbones are
loaded separately and remain unchanged.
| folder | backbone | configuration |
|---|---|---|
llava15_L10_PEFT/ | liuhaotian/llava-v1.5-7b | single layer L10 (paper main) |
llava15_stack_L3_6_7_10_19_PEFT/ | liuhaotian/llava-v1.5-7b | 5-layer stack {3,6,7,10,19} (paper main) |
crossarch_phi3_L20/ | xtuner/llava-phi-3-mini-hf | Appendix F Track A, L20 |
crossarch_qwen25_L4/ | Zhang199/TinyLLaVA-Qwen2.5-3B-SigLIP | Appendix F Track B, L4 (prior 1.25) |
Each folder ships the matching sink_cfg.json. The two LLaVA-1.5 folders keep the _PEFT suffix because the loader activates gate-only loading when the model_base directory name contains PEFT. Usage instructions:
github.com/JH-GEECS/lsg_public.
- License
- apache-2.0
- Created
- Jul 26, 2026
- Updated
- Aug 5, 2026