qwen3-5-2b-base-mtp / README.md
ttupper75035's picture
Add self-describing model card (mtp-sidecar)
877c6ee verified
|
Raw
History Blame Contribute Delete
1.93 kB
metadata
base_model: Qwen/Qwen3.5-2B-Base
tags:
  - mtp-sidecar
  - skulk
  - foxlight
license: apache-2.0
license_link: https://huggingface.co/Qwen/Qwen3.5-2B-Base/blob/main/LICENSE
foxlight:
  artifact_type: mtp-sidecar
  source_repo: Qwen/Qwen3.5-2B-Base
  source_revision: b1485b2fa6dfa1287294f269f5fb618e03d52d7c
  target_model: Qwen/Qwen3.5-2B-Base
  extracted_with: skulk-weights-publisher 0.1.0
  generated_at: '2026-06-03T00:27:04Z'

FoxlightAI/qwen3-5-2b-base-mtp

This repository contains an MTP speculative-decoding sidecar derived from Qwen/Qwen3.5-2B-Base. It is not a standalone model — it provides the multi-token-prediction heads used by Skulk to speculatively decode for the target model Qwen/Qwen3.5-2B-Base. The heads ship at full precision (bf16, unquantized) — they are the speculative drafter, where precision drives draft acceptance — so there is one sidecar per base model and it serves every quantization of the target.

Provenance

Field Value
Artifact type mtp-sidecar
Source model Qwen/Qwen3.5-2B-Base
Source revision b1485b2fa6dfa1287294f269f5fb618e03d52d7c
Target model Qwen/Qwen3.5-2B-Base
Extracted with skulk-weights-publisher 0.1.0
Generated 2026-06-03T00:27:04Z

Usage

Skulk loads this sidecar (mtp.safetensors) alongside the target model to enable MTP speculative decoding. It is referenced from the Skulk Weights Publisher catalog and fetched automatically by the Skulk shard downloader; it is not intended to be loaded standalone.

License

This artifact is derived from Qwen/Qwen3.5-2B-Base and is published under that model's original license (apache-2.0), preserved unchanged. Refer to the source model's card for the full terms.