| --- |
| license: apache-2.0 |
| base_model: laion/r2egym-nl2bash-stack-bugsseq-fixthink-again |
| tags: |
| - reinforcement-learning |
| - code |
| - swesmith |
| - rl |
| - rloo |
| datasets: |
| - DCAgent/swesmith-oracle-verified-120s-2500 |
| language: |
| - en |
| pipeline_tag: text-generation |
| library_name: transformers |
| --- |
| |
| # SweSmith-8B-SFT-Rope-step62 |
|
|
| RL-trained Qwen3-8B on SWEsmith tasks (65k context with YaRN rope scaling factor=4.0, 62 steps). Best evaluated at 65k context. |
|
|
| ## Training Details |
|
|
| - **Base model**: [laion/r2egym-nl2bash-stack-bugsseq-fixthink-again](https://huggingface.co/laion/r2egym-nl2bash-stack-bugsseq-fixthink-again) (Qwen3-8B SFT) |
| - **Training method**: RLOO-N |
| - **Training data**: 2,500 SWEsmith tasks (oracle-verified, 120s timeout) |
| - **Framework**: BenSkyRL + Harbor |
| - **Sandbox**: Apptainer containers with proxychains for internet access |
|
|
|
|
|
|
