laion/rl_r2egym-nl2bash-swesmith-pymethods2test_terminus-structured
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity
Files
b18f395cebf6dd8da4f6249dcc6c56aa147e32b6
rl_r2egym-nl2bash-swesmith-…/README.md
ModelHub XC b18f395ceb 初始化项目，由ModelHub XC社区提供模型 
Model: laion/rl_r2egym-nl2bash-swesmith-pymethods2test_terminus-structured
Source: Original Platform
2026-05-07 01:08:49 +08:00

1.6 KiB
Raw Blame History

license, base_model, tags, language, pipeline_tag, library_name
license base_model tags language pipeline_tag library_name
apache-2.0 laion/r2egym-nl2bash-stack-bugsseq-fixthink-again
reinforcement-learning
code
r2egym,pymethods2test,swesmith,nl2bash
rl
rloo-n
terminus-structured
en
text-generation transformers

rl_r2egym-nl2bash-swesmith-pymethods2test_terminus-structured

RL-trained Qwen3-8B with structured tool calls.

Training pipeline: SFT (r2egym+nl2bash+swesmith) → RL mixed dataset (37 steps) → RL full r2egym (55 steps) → RL pymethods2test (110 steps).

Key results:

  • SWEBench-100: 42% pass@3 (vs 37% base with terminus-2)
  • Pymethods2test: 94-100% pass@8
  • 14 SWEBench tasks solved that base model cannot
  • Trained with terminus-structured agent (bash, view, edit, create, search tools)

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_r2egym-nl2bash-swesmith-pymethods2test_terminus-structured")
tokenizer = AutoTokenizer.from_pretrained("laion/rl_r2egym-nl2bash-swesmith-pymethods2test_terminus-structured")