Downloads · 30 days
363
50% of all-time downloads
RestoreKV-Qwen3-8B_plus
higokri/RestoreKV-Qwen3-8B_plus
RestoreKV-Qwen3-8B_plus is a machine learning model from higokri. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as cc-by-nc-4.0.
PEFT LoRA adapter + restore-token embeddings for RestoreKV (paper), a budget-matched, single-pass plug-in that recovers full-cache behavior under aggressive KV cache eviction on top of KVzip.
All-time downloads
722
Public
Repo size
43.8 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors43.8 MB · 100%
At a glance
- Library
- peft
- License
- cc-by-nc-4.0
- Access
- Public
- Created
- Aug 6, 2026
- Updated
- Aug 6, 2026
- SHA
- 22261ed3
Base models
Model card
From the Hugging Face model README
RestoreKV-Qwen3-8B_plus
PEFT LoRA adapter + restore-token embeddings for RestoreKV (paper), a budget-matched, single-pass plug-in that recovers full-cache behavior under aggressive KV cache eviction on top of KVzip.
- Base model:
Qwen/Qwen3-8B— base scorer: KVzip+ adapter_model.safetensors: rank-8 LoRA (α=16) on q/k/v/o/gate/up/down projrestore_embeddings.safetensors: 8 learned restore-token embeddings
Load via the RestoreKVPress in NVIDIA/kvpress.
License
CC BY-NC 4.0 (distilled with LongAlpaca-derived data; research / non-commercial).
- Library
- peft
- License
- cc-by-nc-4.0
- Created
- Aug 6, 2026
- Updated
- Aug 6, 2026