Kimi-K2.7-Code EAGLE3 draft

EAGLE3 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).

Single-layer Llama-style EAGLE3 draft (LlamaForCausalLMEagle3, hidden 7168); consumes target aux hidden states at layers [1,29,57].
Target vocab/tokenizer: Kimi-K2.7-Code (vocab 163840); reduced draft vocab 32000 (t2d/d2t mapping, 97.5% token coverage on the training mix).
Checkpoint: epoch_1_step_98000 — Work-in-progress snapshot (epoch_1_step_98000) — training still running.

Intended as the EAGLE3 draft in SGLang speculative decoding paired with the Kimi-K2.7-Code target. Trained as an A/B counterpart to the DFlash draft (cm00cm/Kimi-K2.7-Code-DFlash).

Downloads last month: 31

Safetensors

Model size

1B params

Tensor type

I64

BF16

BOOL

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for cm00cm/Kimi-K2.7-Code-EAGLE3

Base model

moonshotai/Kimi-K2.7-Code

Finetuned

(6)

this model