Downloads · 30 days
31
9% of all-time downloads
rostam-r1-stage13-2
officialmobai/rostam-r1-stage13-2
rostam-r1-stage13-2 is a text generation model from officialmobai. Use it when you need the model to write or continue text. The card lists the license as other.
Rostam R1 Stage 13-2 is the Direct Preference Optimization (DPO) aligned release of the Rostam series, fine-tuned from prog-love/rostam-r1-stage13-1.
All-time downloads
364
Public
Parameters
5.1B
57.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt37 GB · 55%
At a glance
- Task
- Text Generation
- License
- other
- Model type
- gemma4
- Access
- Public
- Created
- Sep 21, 2026
- Updated
- Sep 21, 2026
- SHA
- 0ebc0088
Try a prompt
Base models
Model card
From the Hugging Face model README
🗡️ Rostam R1 Stage 13-2 (DPO Aligned)
Rostam R1 Stage 13-2 is the Direct Preference Optimization (DPO) aligned release of the Rostam series, fine-tuned from prog-love/rostam-r1-stage13-1.
Verified Benchmark Results (PQuAD Test - 8,002 samples):
- Exact Match (EM): 42.08% (+4.89% over Stage 12, +10.59% over Stage 13-1 raw).
- F1 Score: 67.20% (+3.83% over Stage 12).
- False Abstention Rate: 1.23% (Down from 7.24% in Stage 12).
- Repetition Mitigation: Enforced
<|turn|>stop boundaries, eliminating repetition loops.
Training Setup:
- Lineage:
stage12-part2->stage13->stage13-1->stage13-2 - Method: Full-Parameter BF16 DPO (all 5.104B parameters trained)
- Optimizer: Native PyTorch Fused AdamW
- Hardware: 1x NVIDIA RTX PRO 6000 Blackwell Server Edition (96 GB VRAM)
- Task
- Text Generation
- Type
- gemma4
- License
- other
- Created
- Sep 21, 2026
- Updated
- Sep 21, 2026