Downloads · 30 days
49
8% of all-time downloads
HongKi08/DeepSeek-V4-Flash-0731-DSpark-Drafter-GGUF
DeepSeek-V4-Flash-0731-DSpark-Drafter-GGUF is a machine learning model from HongKi08. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
This repository contains a locally requantized DSpark speculative-decoding drafter for DeepSeek V4 Flash 0731. It is not a standalone chat model and must be loaded together with a compatible DeepSeek V4 Flash 0731 mai…
Downloads · 30 days
49
8% of all-time downloads
All-time downloads
584
Public
Repo size
7 GB
Likes
0
Public
Click a slice to open those files.
.gguf7 GB · 100%
From the Hugging Face model README
This repository contains a locally requantized DSpark speculative-decoding drafter for DeepSeek V4 Flash 0731. It is not a standalone chat model and must be loaded together with a compatible DeepSeek V4 Flash 0731 main model.
| File | Size | SHA-256 |
|---|---|---|
dspark-DeepSeek-V4-Flash-0731-EXPERT-Q2_K.gguf | 6.963 GB (6.485 GiB) | 4a05eaa5d94a73c00160bf988b567b55f0b32e2b6f322714eaefe46b828b218c |
The source drafter was dspark-DeepSeek-V4-Flash-0731-Q8_0.gguf from unsloth/DeepSeek-V4-Flash-0731-GGUF.
This is a mixed quantization produced with llama-quantize:
blk.[0-2].ffn_(down|gate|up)_exps.weight: Q2_Kmarkov_w1.weight, markov_w2.weight: F16Q8_0--allow-requantize --purellama-quantize \
--allow-requantize \
--pure \
--tensor-type 'blk\.[0-2]\.ffn_(down|gate|up)_exps\.weight=q2_k' \
--tensor-type 'markov_w[12]\.weight=f16' \
dspark-DeepSeek-V4-Flash-0731-Q8_0.gguf \
dspark-DeepSeek-V4-Flash-0731-EXPERT-Q2_K.gguf \
Q8_0
Use a llama.cpp build with DeepSeek V4 Flash and DSpark support.
llama-server \
-m /models/main/DeepSeek-V4-Flash-0731-UD-Q2_K_XL-00001-of-00003.gguf \
--spec-draft-model /models/draft/dspark-DeepSeek-V4-Flash-0731-EXPERT-Q2_K.gguf \
--spec-type draft-dspark \
--spec-draft-ngl all \
--spec-draft-n-max 3 \
--spec-draft-p-min 0.0 \
--ctx-size 524288 \
--n-gpu-layers all \
--flash-attn on
The local validation configuration used DeepSeek-V4-Flash-0731-UD-Q2_K_XL as the main model and loaded this file through --spec-draft-model.
The upstream model and source GGUF repository declare the MIT license. See: