Downloads · 30 days
9
4% of all-time downloads
laion/a3-rl-laion_nemotron-gym-knowledge-web-search-mcqa-25-8B
a3-rl-laion_nemotron-gym-knowledge-web-search-mcqa-25-8B is a machine learning model from laion. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
RL (fully-async, fan-out K=4) checkpoint trained on laion/nemotron-gym-knowledge-web-search-mcqa, selected by EMA-best (5-period EMA, alpha=1/3) of reward/avgrawreward over the full step-1-80 training curve.
Downloads · 30 days
9
4% of all-time downloads
All-time downloads
223
Public
Parameters
8.2B
32.9 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors16.4 GB · 99%
From the Hugging Face model README
RL (fully-async, fan-out K=4) checkpoint trained on
laion/nemotron-gym-knowledge-web-search-mcqa, selected by EMA-best
(5-period EMA, alpha=1/3) of reward/avg_raw_reward over the full
step-1->80 training curve.
laion/GLM-4_7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k-fixthink (Qwen3-8B architecture)Training-time Daytona/Harbor rollouts for this run are uploaded as a companion dataset: open-athena/a3-rl-laion_nemotron-gym-knowledge-web-search-mcqa
The dataset contains the last episode of each trial (per
make_and_upload_trace_dataset --episodes last) — the same rollouts
the policy was trained on after rollback / truncation.