deepseek-v4-pro-mtp / README.md
ttupper75035's picture
Add self-describing model card (mtp-sidecar)
75c6b02 verified
|
Raw
History Blame Contribute Delete
1.91 kB
metadata
base_model: deepseek-ai/DeepSeek-V4-Pro
tags:
  - mtp-sidecar
  - skulk
  - foxlight
license: mit
foxlight:
  artifact_type: mtp-sidecar
  source_repo: deepseek-ai/DeepSeek-V4-Pro
  source_revision: 89d501aed998d33fa4f4702102ec1bb2331e10f6
  target_model: deepseek-ai/DeepSeek-V4-Pro
  extracted_with: skulk-weights-publisher 0.1.0
  generated_at: '2026-06-03T19:21:34Z'

FoxlightAI/deepseek-v4-pro-mtp

This repository contains an MTP speculative-decoding sidecar derived from deepseek-ai/DeepSeek-V4-Pro. 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-Pro. 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-Pro
Source revision 89d501aed998d33fa4f4702102ec1bb2331e10f6
Target model deepseek-ai/DeepSeek-V4-Pro
Extracted with skulk-weights-publisher 0.1.0
Generated 2026-06-03T19:21:34Z

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-Pro and is published under that model's original license (mit), preserved unchanged. Refer to the source model's card for the full terms.