Kimi-K2.7-Code DFlash draft

DFlash speculative-decoding draft model for moonshotai/Kimi-K2.7-Code, trained with SpecForge (PR #593) on NVIDIA Nemotron-Post-Training-Dataset-v2 (stem+chat+math+code).

6-layer Qwen3-style draft (hidden 7168); consumes target hidden states at layers [1,12,24,35,47,58]; block_size 8.
Target vocab/tokenizer: Kimi-K2.7-Code (vocab 163840, mask_token_id 163838).
Checkpoint: epoch_2_step_160000 — Work-in-progress snapshot (epoch_2_step_160000) — training still running.

Load with trust_remote_code=True (model code in dflash.py). Intended as the draft in SGLang DFlash speculative decoding paired with the Kimi-K2.7-Code target.

Downloads last month: -

Safetensors

Model size

3B params

Tensor type

BF16

Model tree for cm00cm/Kimi-K2.7-Code-DFlash

Base model

moonshotai/Kimi-K2.7-Code

Finetuned

(5)

this model