Downloads · 30 days
7
35% of all-time downloads
rstar_coder_32m_lora_olmo3_1025_7b_base
modrill/rstar_coder_32m_lora_olmo3_1025_7b_base
rstar_coder_32m_lora_olmo3_1025_7b_base is a machine learning model from modrill. 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 peft. The card lists the license as apache-2.0.
Immutable LoRA adapter freeze (ADAPTERONLYNOMERGE).
All-time downloads
20
Public
Repo size
640 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors640 MB · 100%
At a glance
- Library
- peft
- License
- apache-2.0
- Access
- Public
- Created
- Aug 29, 2026
- Updated
- Aug 29, 2026
- SHA
- 2f08e484
Base models
Model card
From the Hugging Face model README
rstar_coder_32m_lora_olmo3_1025_7b_base
Immutable LoRA adapter freeze (ADAPTER_ONLY_NO_MERGE).
- Base:
allenai/Olmo-3-1025-7B@a81bae42db3975be1671e27b9c9a56da1a9f980f - Adapter tree SHA-256:
4964d87b49be67f1b80a626c5ded0c482c69553ec6799eda2d073e0f8e9e2569 - Immutable tag:
freeze-4964d87b49be67f1 - Dose: 32018321 assistant target tokens (step 419)
- Recipe SHA-256:
b2fb6275575e08e1b07d482d9f12418b22f5588c55b28bbf9dec29fb3e1fadf9 - Data READY manifest SHA-256:
397e8ba94a5d421ee960344e3e45e431ea90174ff9c0e459f5d9bb57137caf97 - DEV256 (seed 3407): pass@1 = 0.2734375 (70/256)
- Trained on GPU: 1
Do not merge unless you intentionally create a separate merged revision. Load with PEFT against the pinned base revision above.
- Library
- peft
- License
- apache-2.0
- Created
- Aug 29, 2026
- Updated
- Aug 29, 2026