Downloads · 30 days
43
2% of all-time downloads
a3-rl-DCAgent_exp_rpt_pymethods2test-v3-10-8B
laion/a3-rl-DCAgent_exp_rpt_pymethods2test-v3-10-8B
a3-rl-DCAgent_exp_rpt_pymethods2test-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 (SkyRL) checkpoint trained from base laion/GLM-47-swesmith-sandboxes-withtests-oracleverified120s-maxeps-131k-fixthink on dataset DCAgent/exprptpymethods2test-v3.
All-time downloads
2.8K
Public
Parameters
8.2B
16.5 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
- 35375332
Base models
Model card
From the Hugging Face model README
a3-rl-DCAgent_exp_rpt_pymethods2test-v3 (global_step 10, 8B)
RL (SkyRL) checkpoint trained from base
laion/GLM-4_7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k-fixthink
on dataset DCAgent/exp_rpt_pymethods2test-v3.
Checkpoint selected at global_step 10 by 5-period reward-EMA (alpha=1/3) over the full stitched step sequence. Steps 15-25 were degenerate resume-creep links (data consumption mismatch, no real reward), so the last genuinely-trained aligned checkpoint (step 10) was chosen.
Training Traces
Training-time Daytona/Harbor rollouts for this run are uploaded as a companion dataset: open-athena/a3-rl-DCAgent_exp_rpt_pymethods2test-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