Instructions to use OpenHands/CodeScout-1.7B-RFT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpenHands/CodeScout-1.7B-RFT with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="OpenHands/CodeScout-1.7B-RFT")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("OpenHands/CodeScout-1.7B-RFT")
model = AutoModelForCausalLM.from_pretrained("OpenHands/CodeScout-1.7B-RFT")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use OpenHands/CodeScout-1.7B-RFT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OpenHands/CodeScout-1.7B-RFT"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OpenHands/CodeScout-1.7B-RFT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/OpenHands/CodeScout-1.7B-RFT

SGLang

How to use OpenHands/CodeScout-1.7B-RFT with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "OpenHands/CodeScout-1.7B-RFT" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OpenHands/CodeScout-1.7B-RFT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "OpenHands/CodeScout-1.7B-RFT" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OpenHands/CodeScout-1.7B-RFT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use OpenHands/CodeScout-1.7B-RFT with Docker Model Runner:
```
docker model run hf.co/OpenHands/CodeScout-1.7B-RFT
```

CodeScout-1.7B-RFT / README.md

gneubig

Update CodeScout arXiv citation

bb625ea verified about 2 months ago

preview code

raw

history blame contribute delete

4.93 kB

	---
	library_name: transformers
	license: apache-2.0
	language:
	- en
	base_model: Qwen/Qwen3-1.7B
	pipeline_tag: text-generation
	tags:
	- code-search
	- code-localization
	- reinforcement-learning
	- agent
	- software-engineering
	- GSPO
	- OpenHands
	- SWE-Bench
	datasets:
	- OpenHands/SWE-smith-py-code-search
	- OpenHands/SWE-Gym-code-search
	- OpenHands/CodeScout_Training_Rollouts
	---

	# CodeScout-1.7B-RFT

	[📄 Paper](https://arxiv.org/abs/2603.17829) • [💻 Code](https://github.com/OpenHands/codescout) • [🤗 Collection](https://huggingface.co/collections/OpenHands/codescout-69b9a6adcf21f348f4db937f)

	Pre-RL checkpoint — rejection fine-tuned on expert trajectories from CodeScout-14B.

	<p align="center">
	<img src="codescout_overview.png" alt="CodeScout Overview" width="100%">
	</p>

	CodeScout-1.7B-RFT is part of the CodeScout family of open-source RL-trained code search agents.
	CodeScout models achieve state-of-the-art repository-level code localization using nothing more than a standard Unix terminal — no static analysis, no repository graphs, no language-specific tooling.

	## Key Highlights

	- Warm-start checkpoint for [CodeScout-1.7B](https://huggingface.co/OpenHands/CodeScout-1.7B) RL training
	- Distilled from CodeScout-14B expert trajectories with rejection sampling
	- Useful for researchers studying the effect of RFT vs. RL in agent training pipelines
	- Can be used as a base for custom RL experiments on code search

	## Results

	Performance on SWE-Bench code localization (instance-averaged F1 scores):


	\| Benchmark \| CodeScout-1.7B \| CodeScout-4B \| CodeScout-14B \|
	\|---\|---\|---\|---\|
	\| SWE-Bench Verified — File F1 \| 55.46 \| 68.52 \| 68.57 \|
	\| SWE-Bench Verified — Func F1 \| 28.22 \| 36.78 \| 40.32 \|
	\| SWE-Bench Pro — File F1 \| 40.96 \| 51.77 \| 53.63 \|
	\| SWE-Bench Pro — Func F1 \| 18.24 \| 29.03 \| 28.74 \|
	\| SWE-Bench Lite — File F1 \| 56.57 \| 67.03 \| 71.84 \|
	\| SWE-Bench Lite — Func F1 \| 27.07 \| 39.87 \| 44.43 \|


	<p align="center">
	<img src="f1_vs_params_file.png" alt="File-level F1 vs Model Size" width="48%">
	<img src="f1_vs_params_function.png" alt="Function-level F1 vs Model Size" width="48%">
	</p>

	<p align="center"><em>Code localization performance on SWE-Bench Verified. CodeScout (⭐) achieves superior or competitive results over larger open-source LLMs and narrows the gap with closed-source frontier models.</em></p>

	## Training

	CodeScout-1.7B-RFT is the intermediate checkpoint produced by rejection fine-tuning (RFT) `Qwen3-1.7B` on expert trajectories from CodeScout-14B, before the final RL stage.

	- Teacher model: [CodeScout-14B](https://huggingface.co/OpenHands/CodeScout-14B)
	- Source trajectories: Rollouts from CodeScout-14B on 7,700 training instances
	- Filtered data: 4K trajectories with perfect scores (F1 = 1.0 at file, module, and function level)
	- SFT epochs: 1
	- Learning rate: 5e-5 with cosine scheduler (warmup ratio 0.1)
	- Batch size: 8
	- Optimizer: AdamW
	- Framework: [veRL](https://github.com/volcengine/verl)

	This checkpoint serves as the starting point for RL training of [CodeScout-1.7B](https://huggingface.co/OpenHands/CodeScout-1.7B).

	## How It Works

	CodeScout uses the OpenHands-Bash scaffold — an agent equipped with only a `Terminal` tool (supporting standard Unix commands like `rg`, `find`, `grep`, `ls`) and a `LocalizationFinish` tool for structured output submission. The agent iteratively navigates the repository to identify relevant files, classes, and functions related to a given issue.

	The model is trained with GSPO (Group Sequence Policy Optimization) using multi-level F1 rewards at the file, module, and function level.

	## Intended Use

	CodeScout-1.7B-RFT is designed for repository-level code localization: given a GitHub issue description and a code repository, it identifies the relevant files, classes, and functions that need to be modified. It is intended to be used as a localization subagent within larger coding agent pipelines.

	## Limitations

	- Trained and evaluated exclusively on Python repositories
	- Designed for code localization, not code editing or issue resolution
	- Performance may vary on repositories significantly different from the training distribution
	- Requires the OpenHands-Bash scaffold for optimal performance

	## Citation

	```bibtex
	@misc{sutawika2026codescouteffectiverecipereinforcement,
	title={CodeScout: An Effective Recipe for Reinforcement Learning of Code Search Agents},
	author={Lintang Sutawika and Aditya Bharat Soni and Bharath Sriraam R R and Apurva Gandhi and Taha Yassine and Sanidhya Vijayvargiya and Yuchen Li and Xuhui Zhou and Yilin Zhang and Leander Melroy Maben and Graham Neubig},
	year={2026},
	eprint={2603.17829},
	archivePrefix={arXiv},
	primaryClass={cs.SE},
	url={https://arxiv.org/abs/2603.17829},
	}
	```