BayesRL

Qwen-B3PO-7B

Deploy Dedicated

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more

Container

Run this model inference with full control and performance in your environment.

Learn more

Get help setting up a custom Dedicated Endpoints.

Talk with our engineer to get a quote for reserved GPU instances with discounts.

Training


Base / warm-start	`BayesRL/Qwen2.5Math-IVON-SFT-7B`
Foundation model	`Qwen/Qwen2.5-Math-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)

Evaluation

Evaluated on AIME 2024–2026, MATH-500, AMC 2023, and Minerva. See the paper for full results.

Usage

python
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("BayesRL/Qwen-B3PO-7B")
tok = AutoTokenizer.from_pretrained("BayesRL/Qwen-B3PO-7B")

Citation

bibtex
@misc{venkatkrishna2026parameter,
      title={Parameter Exploration for RLVR via Variational Learning},
      author={Vatsal Venkatkrishna and Nico Daheim and Iryna Gurevych},
      year={2026},
}