Downloads · 30 days
23
7% of all-time downloads
ablation-pymethods2test-seqmean-arm0-30-8B
laion/ablation-pymethods2test-seqmean-arm0-30-8B
ablation-pymethods2test-seqmean-arm0-30-8B is a text generation model from laion. Use it when you need the model to write or continue text. It is set up for transformers.
RL (SkyRL GRPO) checkpoint from the sequence-mean / RLOO-n (arm0) ablation of the a3-successor study. The policy loss uses lossreduction=sequencemean with the advantageestimator=rloon (RLOO-n) estimator, contrasting w…
All-time downloads
342
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
- Task
- Text Generation
- Library
- transformers
- Model type
- qwen3
- Access
- Public
- Created
- Jun 8, 2026
- Updated
- Sep 4, 2026
- SHA
- bc461d20
Try a prompt
Base models
Model card
From the Hugging Face model README
ablation-pymethods2test-seqmean-arm0-30-8B
RL (SkyRL GRPO) checkpoint from the sequence-mean / RLOO-n (arm0) ablation of
the a3-successor study. The policy loss uses loss_reduction=sequence_mean with
the advantage_estimator=rloo_n (RLOO-n) estimator, contrasting with the
token-mean reduction of the a3 series.
- Base model: laion/GLM-4_7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k-fixthink (a Qwen3-8B SFT)
- Training dataset: DCAgent/exp_rpt_pymethods2test-large
- Checkpoint:
global_step_30. - Training: SkyRL GRPO,
hf_save_interval=5, 14x GH200 nodes on JSC Jupiter.
The rl_config.yaml in this repo is the exact launch config used for reproducibility.
This is the step-30 checkpoint of the same run that produced
laion/ablation-pymethods2test-seqmean-arm0-15-8B (step 15).
Training Traces
Training-time Daytona/Harbor rollouts for this run are uploaded as a companion dataset: open-athena/ablation-pymethods2test-seqmean-arm0
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.
- Task
- Text Generation
- Library
- transformers
- Type
- qwen3
- Created
- Jun 8, 2026
- Updated
- Sep 4, 2026