FoxlightAI/deepseek-v4-flash-mtp

This repository contains an MTP speculative-decoding sidecar derived from deepseek-ai/DeepSeek-V4-Flash. It is not a standalone model — it provides the multi-token-prediction heads used by Skulk to speculatively decode for the target model deepseek-ai/DeepSeek-V4-Flash. 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	deepseek-ai/DeepSeek-V4-Flash
Source revision	6976c7ff1b30a1b2cb7805021b8ba4684041f136
Target model	deepseek-ai/DeepSeek-V4-Flash
Extracted with	skulk-weights-publisher 0.1.0
Generated	2026-06-03T16:45:17Z

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 deepseek-ai/DeepSeek-V4-Flash and is published under that model's original license (mit), preserved unchanged. Refer to the source model's card for the full terms.