Downloads · 30 days
0
qwen3-8b-speculators
liujonathan24/qwen3-8b-speculators
qwen3-8b-speculators is a machine learning model from liujonathan24. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Speculator models for the Qwen/Qwen3-8B target model.
Access
Public
Updated Apr 24, 2026
Repo size
13.4 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt6.1 GB · 100%
At a glance
- Access
- Public
- Created
- Apr 19, 2026
- Updated
- Apr 24, 2026
- SHA
- 02f3aa9c
Model card
From the Hugging Face model README
Qwen3-8B Speculators (DFlash & FLM)
Speculator models for the Qwen/Qwen3-8B target model.
Architectures
| Model File | mlp_type | Draft Layers | Style |
|---|---|---|---|
dflash_5layer_mix.pt | dflash | 5 | DFlash-style |
flm_5layer_uni.pt | flm | 5 | FLM-style |
Training Data
These models were trained on the regenerated dataset (DFlash-style) derived from Qwen3-8B's own responses to the following sources:
- Nemotron Post-Training V2
- CodeAlpaca
- ShareGPT
- UltraChat-200K
Specifically:
- dflash_5layer_mix: Uses a mixture of datasets and a custom Tau schedule (30% pure noise, 20% grid-aligned, 50% uniform).
- flm_5layer_uni: Uses a uniform Tau schedule and standard dataset mixture.
Details
- Target Model: Qwen/Qwen3-8B
- Sequence Length: 2048
- Batch Size: 5
- Draft Layers: 5 (despite some folder naming suggesting 4, internal config confirms 5)
Trained at Princeton AILab.
- Created
- Apr 19, 2026
- Updated
- Apr 24, 2026