metadata
license: apache-2.0
language:
- en
tags:
- qwen3
- qwen
- causal-lm
- transformers
- instruction-tuning
- sft
- agents
- code
library_name: transformers
pipeline_tag: text-generation
base_model: Qwen/Qwen3-32B
model_name: Qwen3-32B-ABC
Qwen3-32B-ABC
Qwen3-32B-ABC is a supervised fine-tuned (SFT) variant of Qwen/Qwen3-32B, trained for agentic backend coding and tool-using / instruction-following behaviors.
Model Details
- Model name:
Qwen3-32B-ABC - Base model:
Qwen/Qwen3-32B - Model type: Causal Language Model (decoder-only)
- Training method: Agentic Supervised Fine-Tuning (SFT)
Training Data
This model was fine-tuned on nex-agi/agent-sft.
Please refer to the dataset card for detailed documentation, licensing, and usage constraints.
Performance on ABC-Bench
Following the ABC-Bench paper’s evaluation protocol:
| Model | Setting | Average Pass@1 (%, 3 attempts) |
|---|---|---|
| Qwen3-32B-ABC | w/ SFT | 33.8% |
| Qwen3-32B | w/o SFT | 8.9% |
Intended Use
Qwen3-32B-ABC is intended for:
- Agent-style instruction following for backend development tasks
- Code editing / patch generation in real repositories
- Command-line oriented debugging and step-by-step problem solving
- Research on automated software engineering and agent evaluation
Usage
Transformers (Python)
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
model_id = "OpenMOSS-Team/Qwen3-32B-ABC"
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
model_id,
torch_dtype=torch.bfloat16,
device_map="auto",
trust_remote_code=True,
)
prompt = "Write a FastAPI endpoint that returns health status as JSON."
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
with torch.no_grad():
output = model.generate(
**inputs,
max_new_tokens=256,
do_sample=True,
temperature=0.7,
top_p=0.9,
)
print(tokenizer.decode(output[0], skip_special_tokens=True))
Citation
@misc{yang2026abcbenchbenchmarkingagenticbackend,
title={ABC-Bench: Benchmarking Agentic Backend Coding in Real-World Development},
author={Jie Yang and Honglin Guo and Li Ji and Jiazheng Zhou and Rui Zheng and Zhikai Lei and Shuo Zhang and Zhiheng Xi and Shichun Liu and Yuxin Wang and Bo Wang and Yining Zheng and Tao Gui and Xipeng Qiu},
year={2026},
eprint={2601.11077},
archivePrefix={arXiv},
primaryClass={cs.SE},
url={https://arxiv.org/abs/2601.11077},
}
Acknowledgements
- Base model:
Qwen/Qwen3-32B - Training dataset:
nex-agi/agent-sft