Downloads · 30 days
67
19% of all-time downloads
dspark-qwen3-8b
mpashkovskii/dspark-qwen3-8b
dspark-qwen3-8b is a machine learning model from mpashkovskii. 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
351
Public
Parameters
1.8B
49 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.pt4.4 GB · 54%
Parameter types
How the weights are stored.
BF161.8B · 100%
Base models
Model card
From the Hugging Face model README
DSpark Speculator for Qwen/Qwen3-8B
Trained using speculators with the DSpark algorithm (DFlash parallel backbone + Markov head + confidence head).
Usage
# Direct deployment (speculators config auto-detected)
vllm serve mpashkovskii/dspark-qwen3-8b
# Or explicit speculative config
vllm serve Qwen/Qwen3-8B \
--speculative-config '{"method": "dspark", "model": "mpashkovskii/dspark-qwen3-8b"}'
Training Configuration
| Parameter | Value |
|---|---|
| Algorithm | DSpark (DFlash + Markov head + confidence head) |
| Verifier | Qwen/Qwen3-8B |
| Block Size | 3 |
| Draft Layers | 5 |
| Hidden Size | 4096 |
| Markov Rank | 256 |
| Markov Head Type | vanilla |
| Confidence Head | True |
| Target Layer IDs | [2, 10, 18, 26, 34] |
| CE Loss α | 0.1 |
| TV Loss α | 0.9 |
| Confidence Loss α | 1.0 |
Evaluation Results
| Metric | Value |
|---|---|
| Full Acceptance Rate | 0.6738 |
| Per-Position Acceptance Rate | 0.6602 |
| Total Loss | 0.0161 |
| CE Loss | 0.0258 |
| TV Loss | 0.0060 |
| Confidence Loss | 0.3979 |
Per-Position Acceptance
| Position | Acceptance Rate |
|---|---|
| 1 | 0.7494 |
| 2 | 0.5981 |
- Library
- speculators
- License
- apache-2.0
- Created
- Jul 5, 2026
- Updated
- Jul 8, 2026