Downloads · 30 days
26
1% of all-time downloads
Kimi-K2.7-Code-DFlash
cm00cm/Kimi-K2.7-Code-DFlash
Kimi-K2.7-Code-DFlash is a feature extraction model from cm00cm. Use it when you need embeddings to search or compare text. It is set up for transformers. The card lists the license as other.
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).
All-time downloads
2.4K
Public
Parameters
3.5B
7 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors7 GB · 100%
At a glance
- Task
- Feature Extraction
- Library
- transformers
- License
- other
- Model type
- qwen3
- Access
- Public
- Created
- Jun 27, 2026
- Updated
- Jun 29, 2026
- SHA
- 07290209
Base models
Model card
From the Hugging Face model README
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.
- Task
- Feature Extraction
- Library
- transformers
- Type
- qwen3
- License
- other
- Created
- Jun 27, 2026
- Updated
- Jun 29, 2026