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 (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
Downloads last month
277
Safetensors
Model size
8B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for laion/SweSmith-8B-SFT-Rope-step62

Base model

Qwen/Qwen3-8B-Base
Finetuned
Qwen/Qwen3-8B
Finetuned
(2)
this model