ModelÜberprüftExtern

Kimi K2.7 Code DFlash

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).

Quellehuggingface.co/cm00cm/Kimi-K2.7-Code-DFlash/tree/07290209664305eae6c119a3c0ab5c1c8743a40b

ArtOtherBasismodellmoonshotai/Kimi-K2.7-CodeVersionRevision 0729020Verleger@cm00cmCBewertung

Modellquelle

Art: Other
Dateigröße: 6,48 GB
Basismodell: moonshotai/Kimi-K2.7-Code
Version: vRevision 0729020
Aktualisiert: 2. Okt. 2026
Verleger: @cm00cm
Downloads: 28
Quelle: Hugging Face

Quellenbeschreibung

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_4_step_334000 — Work-in-progress snapshot (epoch_4_step_334000) — 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.

Quellen

1 Quelle

Hugging FacePrimärVersion 07290209664305eae6c119a3c0ab5c1c8743a40b

huggingface.co/cm00cm/Kimi-K2.7-Code-DFlash/tree/07290209664305eae6c119a3c0ab5c1c8743a40b

Verifiziert 19. Aug.

Modellartefakte

1 Artefakt

model.safetensors

safetensors · 6,48 GB · SHA-256 a2602716a72c…b50c · Hugging Face

Herunterladen

Quellenauszüge

3 Auszüge

Readme11. Julihuggingface.co/cm00cm/Kimi-K2.7-Code-DFlash

--- license: other base_model: moonshotai/Kimi-K2.7-Code library_name: transformers tags: - speculative-decoding - dflash - eagle - draft-model - kimi-k2 - specforge --- # Kimi-K2.7-Code DFlash draft DFlash speculative-decoding **draft model** for [moonshotai/Kimi-K2.7-Code](https://huggingface.co/moonshotai/Kimi-K2.7-Code), trained with [SpecForge](https://github.com/sgl-project/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_4_step_334000 — **Work-in-progress snapshot (epoch_4_step_334000)** — 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.

Note19. Aug.huggingface.co/cm00cm/Kimi-K2.7-Code-DFlash

Source context: 28 downloads · 1 likes · Pipeline feature-extraction · Library transformers · Repo cm00cm/Kimi-K2.7-Code-DFlash

Note18. Julihuggingface.co/cm00cm/Kimi-K2.7-Code-DFlash

Source context: 2326 downloads · 1 likes · Pipeline feature-extraction · Library transformers · Repo cm00cm/Kimi-K2.7-Code-DFlash