RestoreKV
Collection
PEFT LoRA adapters for RestoreKV (arXiv:2608.01247): budget-matched learned restoration on top of KVzip. • 4 items • Updated
RestoreKV-Llama-3.1-8B-Instruct_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:
meta-llama/Llama-3.1-8B-Instruct— 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).
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for higokri/RestoreKV-Llama-3.1-8B-Instruct_plus
Base model
meta-llama/Llama-3.1-8B Finetuned
meta-llama/Llama-3.1-8B-Instruct