Qwen2.5-7B-Instruct-FP8-Dynamic-TR171

qwen2.5-7b — FP8_DYNAMIC (W8A8-e4m3)

Weight-FP8 checkpoint of Qwen/Qwen2.5-7B-Instruct, produced for the TR171 deployment-time safety-tax benchmark.

Provenance

Reproducing

Producer: research/tr171/expansion/fp8_support_probe.py; environment: research/tr171/expansion/Dockerfile.fp8. The recipe takes no calibration corpus, so there is no dataset or seed to reproduce — only the base checkpoint and the toolchain version.

Known reproducibility gap: llmcompressor was unpinned at build time, so the exact version used on 2026-07-02 is unrecorded. The Dockerfile now pins it. A rebuild may therefore not be bit-identical to this artifact.

Integrity, stated honestly: the 2026-07-02 build recorded no sha256 of its own, and the local build directory is now empty, so no aggregate directory digest exists for it. What is verifiable instead: the per-file sha256 below is read from this repo's Git-LFS metadata, and the mirror was checked against the build record — summing the file sizes in this repo, excluding the generated README.md, NOTICE and .gitattributes, reproduces the matrix's shard_bytes of 8,720,216,729 exactly. So these hashes describe the same bytes the probe measured, and you can verify a download against them directly:

LFS-tracked files only; the small JSON/text files are git blobs and carry no sha256. fp8_support_probe.py now records a real digest at build time, so future shards will not need this reconstruction.

License and notices

Base model Qwen2.5-7B-Instruct is released under Apache 2.0.

This FP8 derivative inherits the upstream terms of Qwen/Qwen2.5-7B-Instruct. Consult the base model's licence before redistributing.