Downloads · 30 days
90
3% of all-time downloads
a3-rl-DCAgent_exp_rpt_unitsyn-python-v3-10-8B
laion/a3-rl-DCAgent_exp_rpt_unitsyn-python-v3-10-8B
a3-rl-DCAgent_exp_rpt_unitsyn-python-v3-10-8B 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 (RLOO, fully-async SkyRL) checkpoint, globalstep 10, selected by 5-period reward-EMA (alpha=1/3) over the full stitched real-step reward trajectory.
All-time downloads
3.2K
Public
Parameters
8.2B
16.6 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors16.4 GB · 99%
At a glance
- Model type
- qwen3
- Access
- Public
- Created
- Jun 1, 2026
- Updated
- Sep 4, 2026
- SHA
- c35b6078
Model card
From the Hugging Face model README
a3-rl-DCAgent_exp_rpt_unitsyn-python-v3 (global_step 10, 8B)
RL (RLOO, fully-async SkyRL) checkpoint, global_step 10, selected by 5-period reward-EMA (alpha=1/3) over the full stitched real-step reward trajectory.
- Base model:
laion/GLM-4_7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k-fixthink(Qwen3-8B arch) - Dataset:
DCAgent/exp_rpt_unitsyn-python-v3 - Training: 2 epochs (data-bounded completion); see
rl_config.txtfor the full launch invocation.
Training Traces
Training-time Daytona/Harbor rollouts for this run are uploaded as a companion dataset: open-athena/a3-rl-DCAgent_exp_rpt_unitsyn-python-v3
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.
- Type
- qwen3
- Created
- Jun 1, 2026
- Updated
- Sep 4, 2026