Downloads · 30 days
14
11% of all-time downloads
laion/a3-rl-laion_nemotron-gym-identity-following-v2-65-8B
a3-rl-laion_nemotron-gym-identity-following-v2-65-8B 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 (GRPO/rloon) finetune trained with SkyRL on Jupiter (a3 series 22).
Downloads · 30 days
14
11% of all-time downloads
All-time downloads
124
Public
Parameters
8.2B
32.8 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors16.4 GB · 100%
From the Hugging Face model README
RL (GRPO/rloo_n) finetune trained with SkyRL on Jupiter (a3 series #22).
reward/avg_raw_reward across the full 80-step run (EMA=0.9996, raw reward at step=1.0000). Run completed its full max_steps=80 at near-perfect reward.Training-time Daytona/Harbor rollouts for this run are uploaded as a companion dataset: open-athena/a3-rl-laion_nemotron-gym-identity-following-v2
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.