Downloads · 30 days
118
50% of all-time downloads
laion/a3-rl-laion_nemotron-gym-instruction-following-structured-75-8B
a3-rl-laion_nemotron-gym-instruction-following-structured-75-8B 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 fine-tune (SkyRL) of laion/GLM-47-swesmith-sandboxes-withtests-oracleverified120s-maxeps-131k-fixthink (Qwen3-8B) on open-athena/nemotron-gym-instruction-following-structured.
Downloads · 30 days
118
50% of all-time downloads
All-time downloads
235
Public
Parameters
8.2B
33 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors16.4 GB · 99%
From the Hugging Face model README
RL fine-tune (SkyRL) of laion/GLM-4_7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k-fixthink (Qwen3-8B)
on open-athena/nemotron-gym-instruction-following-structured.
Checkpoint selected by 5-period EMA (alpha=1/3) of reward/avg_raw_reward over the
full 80-step trajectory (reconstructed across 11 chain-restart .out logs). global_step 75
is the highest-EMA saved export (EMA=0.9512, step reward=0.9902). The run trained the full
max_steps=80 (final reward ~0.92, pass@8 ~0.95), surviving ~5 vLLM crash-restarts.
Training-time Daytona/Harbor rollouts for this run are uploaded as a companion dataset: open-athena/a3-rl-laion_nemotron-gym-instruction-following-structured
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.