clef-flash-FP8 / README.md
aleksblago's picture
docs: link the arXiv paper (2611.15671) (#1)
f25d5b7
|
Raw History Blame Contribute Delete
799 Bytes
metadata
license: apache-2.0
base_model: Cloudflare/clef-flash
base_model_relation: quantized
tags:
  - quantized

clef-flash-FP8

FP8 W8A8, built with llm-compressor, for vLLM. A quantized build of Cloudflare's Clef-flash (9B), made for "The Noise Floor of a Quantization Comparison" by Aleks Blagojevich and Trevor Sunderland (Level5). This isn't an official Cloudflare release.

These builds keep the joint schema head, the vision tower, the norms and the Gated DeltaNet gate projections in BF16. The recipes are in the repository.

Paper: https://arxiv.org/abs/2611.15671

Measurements, recipes and per-record outputs: https://github.com/Level5Tech/clef-quant-bench

The base model is under Apache-2.0. Its LICENSE is included here, and NOTICE says these weights were modified by quantization.