Downloads · 30 days
61
27% of all-time downloads
dspark-gemma-4-31b-it
olka-amd/dspark-gemma-4-31b-it
dspark-gemma-4-31b-it is a machine learning model from olka-amd. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for speculators. The card lists the license as apache-2.0.
Trained using speculators with the DSpark algorithm (DFlash parallel backbone + Markov head + confidence head).
All-time downloads
224
Public
Parameters
4.2B
27.2 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors8.4 GB · 62%
Parameter types
How the weights are stored.
BF164.2B · 100%
Base models
Model card
From the Hugging Face model README
DSpark Speculator for google/gemma-4-31B-it
Trained using speculators with the DSpark algorithm (DFlash parallel backbone + Markov head + confidence head).
Usage
# Direct deployment (speculators config auto-detected)
vllm serve olka-amd/dspark-gemma-4-31b-it
# Or explicit speculative config
vllm serve google/gemma-4-31B-it \
--speculative-config '{"method": "dspark", "model": "olka-amd/dspark-gemma-4-31b-it"}'
Training Configuration
| Parameter | Value |
|---|---|
| Algorithm | DSpark (DFlash + Markov head + confidence head) |
| Verifier | google/gemma-4-31B-it |
| Block Size | 7 |
| Draft Layers | 5 |
| Hidden Size | 5376 |
| Markov Rank | 256 |
| Markov Head Type | vanilla |
| Confidence Head | True |
| Target Layer IDs | [2, 16, 30, 44, 58] |
| CE Loss α | 0.1 |
| TV Loss α | 0.9 |
| Confidence Loss α | 1.0 |
Evaluation Results
| Metric | Value |
|---|---|
| Full Acceptance Rate | 0.6934 |
| Per-Position Acceptance Rate | 0.6663 |
| Total Loss | 0.4404 |
| CE Loss | 0.7204 |
| TV Loss | 0.1543 |
| Confidence Loss | 0.2294 |
Per-Position Acceptance
| Position | Acceptance Rate |
|---|---|
| 0 | 0.8375 |
| 1 | 0.7722 |
| 2 | 0.7216 |
| 3 | 0.6798 |
| 4 | 0.6437 |
| 5 | 0.6129 |
| 6 | 0.5836 |
- Library
- speculators
- License
- apache-2.0
- Created
- Jul 22, 2026
- Updated
- Aug 3, 2026