Instructions to use moxin-org/C2Rust with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use moxin-org/C2Rust with Transformers:

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

pipe = pipeline("text-generation", model="moxin-org/C2Rust")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("moxin-org/C2Rust")
model = AutoModelForMultimodalLM.from_pretrained("moxin-org/C2Rust", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use moxin-org/C2Rust with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "moxin-org/C2Rust"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "moxin-org/C2Rust",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/moxin-org/C2Rust

SGLang

How to use moxin-org/C2Rust 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 "moxin-org/C2Rust" \
    --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": "moxin-org/C2Rust",
		"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 "moxin-org/C2Rust" \
        --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": "moxin-org/C2Rust",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use moxin-org/C2Rust with Docker Model Runner:
```
docker model run hf.co/moxin-org/C2Rust
```

hzeng8 commited on Aug 24

Commit

3a8bd5a

verified ·

1 Parent(s): 8d9d4cb

Update README.md

Browse files

Files changed (1) hide show

README.md +23 -11

README.md CHANGED Viewed

@@ -14,6 +14,7 @@ tags:
 - fine-tuning
 - sactor
 - deepspeed
 ---
 # C2Rust
@@ -24,12 +25,23 @@ behaviorally equivalent Rust. The model is trained with a three-stage curriculum
 an execution-based SACTOR harness that compiles each candidate and compares its behavior with the
 source C program.
-The accompanying technical report is titled **“Fine-Tuning Qwen3.5-27B for C-to-Rust Code
-Translation: A Three-Stage Curriculum of Pretraining, Debugging-Aware SFT, and Task-Specific SFT”**
-(August 2026).
 ## Results
 ### C2Rust translation success rate
 Success Rate (SR) is the percentage of programs that compile and pass every end-to-end test. Scores
@@ -118,6 +130,8 @@ agreement on the supplied test suite, not formal semantic equivalence.
 ## Resources
 - [Benchmark, evaluation harness, and setup instructions](https://github.com/moxin-org/C2Rust)
 - [Base model: Qwen/Qwen3.5-27B](https://huggingface.co/Qwen/Qwen3.5-27B)
 - [SACTOR translation engine](https://github.com/qsdrqs/sactor)
@@ -180,15 +194,13 @@ it for correctness, safety, and maintainability before use.
 ## Citation
-The supplied manuscript has not finalized its individual author list. Until citation metadata is
-released, cite the software artifact:
 ```bibtex
-@software{moxin2026c2rust,
-  title  = {C2Rust: Fine-Tuned Qwen3.5-27B for C-to-Rust Translation},
-  author = {{Moxin Organization}},
-  year   = {2026},
-  url    = {https://github.com/moxin-org/C2Rust}
 }
 ```

 - fine-tuning
 - sactor
 - deepspeed
+- arxiv:2608.13681
 ---
 # C2Rust
 an execution-based SACTOR harness that compiles each candidate and compares its behavior with the
 source C program.
+## Paper
+**[Fine-Tuning Qwen3-27B for C-to-Rust Code Translation: A Three-Stage Curriculum of Pretraining,
+Debugging-Aware SFT, and Task-Specific SFT](https://arxiv.org/abs/2608.13681)**
+Pu Zhao, Changdi Yang, Yixiao Chen, Yi Gao, Yifan Cao, Haochen Zeng, and Yanzhi Wang.<br>
+Northeastern University · EmbodyX Inc · Aibao LLC
+The arXiv title uses “Qwen3-27B”; Section 3 identifies the released source checkpoint as
+`Qwen/Qwen3.5-27B`, which is the identifier used throughout this model card.
 ## Results
+> **87.30% execution-verified C2Rust Success Rate** — a **15.00 percentage-point gain** over the
+> untuned Qwen3.5-27B base at identical model size. The 27B checkpoint also outperforms
+> Qwen3.5-Plus (397B total), MiniMax-M2.5 (230B total), and GLM-5 (744B total) on this benchmark.
 ### C2Rust translation success rate
 Success Rate (SR) is the percentage of programs that compile and pass every end-to-end test. Scores
 ## Resources
+- [Paper: arXiv:2608.13681](https://arxiv.org/abs/2608.13681)
+- [Project website](https://moxin-org.github.io/C2Rust/)
 - [Benchmark, evaluation harness, and setup instructions](https://github.com/moxin-org/C2Rust)
 - [Base model: Qwen/Qwen3.5-27B](https://huggingface.co/Qwen/Qwen3.5-27B)
 - [SACTOR translation engine](https://github.com/qsdrqs/sactor)
 ## Citation
 ```bibtex
+@article{zhao2026c2rust,
+  title   = {Fine-Tuning Qwen3-27B for C-to-Rust Code Translation: A Three-Stage Curriculum of Pretraining, Debugging-Aware SFT, and Task-Specific SFT},
+  author  = {Zhao, Pu and Yang, Changdi and Chen, Yixiao and Gao, Yi and Cao, Yifan and Zeng, Haochen and Wang, Yanzhi},
+  journal = {arXiv preprint arXiv:2608.13681},
+  year    = {2026},
+  doi     = {10.48550/arXiv.2608.13681}
 }
 ```