metadata
license: apache-2.0
base_model: laion/r2egym-nl2bash-stack-bugsseq-fixthink-again
tags:
- reinforcement-learning
- code
- r2egym,swesmith,nl2bash
- rl
- rloo-n
- terminus-structured
language:
- en
pipeline_tag: text-generation
library_name: transformers
rl_mixed-struct-step37_terminus-structured
RL-trained Qwen3-8B with structured tool calls on mixed dataset (200 nl2bash + 500 r2egym + 500 swesmith).
37 RL steps with terminus-structured agent. SWEBench-100: 42% pass@3.
Training Details
- Base model: laion/r2egym-nl2bash-stack-bugsseq-fixthink-again
- Training method: rloo-n with terminus-structured agent (structured tool calls: bash, view, edit, create, search)
- Framework: BenSkyRL + Harbor
- Context: 32k (24k input + 8k output)
- Learning rate: 1e-5
SWEBench-Verified Results (100 tasks, pass@3)
| Model | SWEBench pass@3 |
|---|---|
| Base SFT (terminus-2) | 37% |
| This model (terminus-structured) | See eval results |
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("laion/rl_mixed-struct-step37_terminus-structured")
tokenizer = AutoTokenizer.from_pretrained("laion/rl_mixed-struct-step37_terminus-structured")