Downloads · 30 days
10
29% of all-time downloads
scale-base-blend-rsim-w0p3-detikzify-siglip-s1250
explcre/scale-base-blend-rsim-w0p3-detikzify-siglip-s1250
scale-base-blend-rsim-w0p3-detikzify-siglip-s1250 is a reinforcement learning model from explcre. Use it for the reinforcement learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
RL checkpoint. Base TikZilla-3B (SFT), trained with Dr.GRPO/DAPO against the DSV blenddr verifiable reward (0.7·DSV + 0.3·RenderGraph, both symbolic verifiers -- no learned reward model).
All-time downloads
34
Public
Parameters
3.1B
6.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors6.2 GB · 100%
At a glance
- Task
- Reinforcement Learning
- License
- mit
- Model type
- qwen2
- Access
- Public
- Created
- Aug 2, 2026
- Updated
- Aug 2, 2026
- SHA
- 080ba68f
Model card
From the Hugging Face model README
scale_base_blend_rsim_w0p3_detikzify_siglip @ step 1250
RL checkpoint. Base TikZilla-3B (SFT), trained with Dr.GRPO/DAPO
against the DSV blend_dr verifiable reward (0.7·DSV + 0.3·RenderGraph, both symbolic verifiers --
no learned reward model).
- data:
explcre/datikz_v4_rl_hybrid_428k(427,553 rows, 46.6% Kimi-K3 descriptions / 53.4% DaTikZ-v4vlm_description, tagged per row) - verifier:
explcre/DeTikZifybranchdsv-verifier@c348406 - config: batch 84, rollout n=8, max_response_length 2048, 1500 steps planned
Evaluate with the matching input distribution. The same checkpoint scores differently on
vlmdesc984 vs kimidesc984, and differently again under different TeX/compile-gate versions --
always report the measurement config with the number.
- Task
- Reinforcement Learning
- Type
- qwen2
- License
- mit
- Created
- Aug 2, 2026
- Updated
- Aug 2, 2026