Downloads · 30 days
110
100% of all-time downloads
qwen4b-math-think-taskvector
Montalte/qwen4b-math-think-taskvector
qwen4b-math-think-taskvector is a text generation model from Montalte. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
Unified Qwen3-4B merge artifact for directional math↔code transfer experiments.
All-time downloads
110
Public
Parameters
4.4B
8.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors8.8 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- apache-2.0
- Model type
- qwen3
- Access
- Public
- Created
- Sep 11, 2026
- Updated
- Sep 11, 2026
- SHA
- 49105aff
Try a prompt
Base models
Model card
From the Hugging Face model README
Montalte/qwen4b-math-think-taskvector
Unified Qwen3-4B merge artifact for directional math↔code transfer experiments.
| Field | Value |
|---|---|
| Base | Qwen/Qwen3-4B-Base@906bfd4b4dc7f14ee4320094d8b41684abff8539 |
| Source specialist | modrill/math-think-q4b-20260908 |
| Domain | math |
| Mode | think |
| Method | taskvector |
Method
taskvector = dense source specialist (\theta_s) (full SFT weights; equivalent to applying the complete task vector (\tau_s=\theta_s-\theta_0)).
Uploaded: 2026-09-11.
- Task
- Text Generation
- Library
- transformers
- Type
- qwen3
- License
- apache-2.0
- Created
- Sep 11, 2026
- Updated
- Sep 11, 2026