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.txt
for the full launch invocation.
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.
Runs of laion a3-rl-DCAgent_exp_rpt_unitsyn-python-v3-10-8B on huggingface.co
2.9K
Total runs
8
24-hour runs
25
3-day runs
59
7-day runs
2.9K
30-day runs
More Information About a3-rl-DCAgent_exp_rpt_unitsyn-python-v3-10-8B huggingface.co Model
a3-rl-DCAgent_exp_rpt_unitsyn-python-v3-10-8B huggingface.co is an AI model on huggingface.co that provides a3-rl-DCAgent_exp_rpt_unitsyn-python-v3-10-8B's model effect (), which can be used instantly with this laion a3-rl-DCAgent_exp_rpt_unitsyn-python-v3-10-8B model. huggingface.co supports a free trial of the a3-rl-DCAgent_exp_rpt_unitsyn-python-v3-10-8B model, and also provides paid use of the a3-rl-DCAgent_exp_rpt_unitsyn-python-v3-10-8B. Support call a3-rl-DCAgent_exp_rpt_unitsyn-python-v3-10-8B model through api, including Node.js, Python, http.
a3-rl-DCAgent_exp_rpt_unitsyn-python-v3-10-8B huggingface.co is an online trial and call api platform, which integrates a3-rl-DCAgent_exp_rpt_unitsyn-python-v3-10-8B's modeling effects, including api services, and provides a free online trial of a3-rl-DCAgent_exp_rpt_unitsyn-python-v3-10-8B, you can try a3-rl-DCAgent_exp_rpt_unitsyn-python-v3-10-8B online for free by clicking the link below.
laion a3-rl-DCAgent_exp_rpt_unitsyn-python-v3-10-8B online free url in huggingface.co:
a3-rl-DCAgent_exp_rpt_unitsyn-python-v3-10-8B is an open source model from GitHub that offers a free installation service, and any user can find a3-rl-DCAgent_exp_rpt_unitsyn-python-v3-10-8B on GitHub to install. At the same time, huggingface.co provides the effect of a3-rl-DCAgent_exp_rpt_unitsyn-python-v3-10-8B install, users can directly use a3-rl-DCAgent_exp_rpt_unitsyn-python-v3-10-8B installed effect in huggingface.co for debugging and trial. It also supports api for free installation.
a3-rl-DCAgent_exp_rpt_unitsyn-python-v3-10-8B install url in huggingface.co: