You can deploy this model and start earning money today!

higokri/
RestoreKV-Llama-3.1-8B-Instruct

Name: RestoreKV-Llama-3.1-8B-Instruct
Availability: InStock

meta-llama/Llama-3.1-8B-Instruct

adapter

cc-by-nc-4.0

Views

No views yet

RestoreKV-Llama-3.1-8B-Instruct

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 proj
restore_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).

higokri/RestoreKV-Llama-3.1-8B-Instruct

RestoreKV-Llama-3.1-8B-Instruct

License

higokri/
RestoreKV-Llama-3.1-8B-Instruct