GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
BayesRL
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
BayesRL
Model Tree
BayesRL/Olmo3-IVON-SFT-7B
Input Modalities
Output Modalities
Supported Functionality
| Base / warm-start | BayesRL/Olmo3-IVON-SFT-7B |
| Foundation model | allenai/Olmo-3-1025-7B |
| Algorithm | B3PO (GRPO + IVON, single perturbation per step) |
| RL data | DAPO-Math-17k |
| Optimizer | IVON, lr 1.0, ESS (λ) 1e10 |
| Hardware | 8× NVIDIA H200 (144 GB) |
Evaluated on AIME 2024–2026, MATH-500, AMC 2023, and Minerva. See the paper for full results.
Loads as a standard causal LM:
python
from transformers import AutoModelForCausalLM, AutoTokenizer model = AutoModelForCausalLM.from_pretrained("BayesRL/Olmo3-B3PO-7B-ESS1e10")tok = AutoTokenizer.from_pretrained("BayesRL/Olmo3-B3PO-7B-ESS1e10")bibtex
@misc{venkatkrishna2026parameterexploration, title={Parameter Exploration for RLVR via Variational Learning}, author={Vatsal Venkatkrishna and Nico Daheim and Iryna Gurevych}, year={2026}, eprint={2608.09805}, archivePrefix={arXiv}, primaryClass={cs.LG}, url={https://arxiv.org/abs/2608.09805}, }@misc{venkatkrishna2026parameterexploration, title={Parameter Exploration for RLVR via Variational Learning}, author={Vatsal Venkatkrishna and Nico Daheim and Iryna Gurevych}, year={2026}, eprint={2608.09805}, archivePrefix={arXiv}, primaryClass={cs.LG}, url={https://arxiv.org/abs/2608.09805}, }