Instructions to use Multilingual-Multimodal-NLP/LoopCoder-V2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Multilingual-Multimodal-NLP/LoopCoder-V2 with Transformers:

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

pipe = pipeline("text-generation", model="Multilingual-Multimodal-NLP/LoopCoder-V2", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Multilingual-Multimodal-NLP/LoopCoder-V2", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Multilingual-Multimodal-NLP/LoopCoder-V2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Multilingual-Multimodal-NLP/LoopCoder-V2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Multilingual-Multimodal-NLP/LoopCoder-V2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Multilingual-Multimodal-NLP/LoopCoder-V2

SGLang

How to use Multilingual-Multimodal-NLP/LoopCoder-V2 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 "Multilingual-Multimodal-NLP/LoopCoder-V2" \
    --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": "Multilingual-Multimodal-NLP/LoopCoder-V2",
		"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 "Multilingual-Multimodal-NLP/LoopCoder-V2" \
        --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": "Multilingual-Multimodal-NLP/LoopCoder-V2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Multilingual-Multimodal-NLP/LoopCoder-V2 with Docker Model Runner:
```
docker model run hf.co/Multilingual-Multimodal-NLP/LoopCoder-V2
```

nielsr HF Staff commited on about 9 hours ago

Commit

adda844

verified ·

1 Parent(s): f8643c8

Add links to paper and GitHub

Browse files

Hi! I'm Niels from the Hugging Face community team. This PR adds links to the official research paper and the GitHub repository to the model card, making it easier for users to find the original source code and research details. I've also updated the citation format to match the official repository.

Files changed (1) hide show

README.md +13 -7

README.md CHANGED Viewed

@@ -1,6 +1,6 @@
 ---
-license: apache-2.0
 library_name: transformers
 pipeline_tag: text-generation
 tags:
 - code
@@ -16,9 +16,11 @@ tags:
 # LoopCoder-V2
 LoopCoder-v2 is a 7B instruction-tuned code model based on the Parallel Loop Transformer (PLT). The model studies test-time computation scaling through repeated application of shared Transformer blocks while keeping the parameter count fixed.
-The released checkpoint is the two-loop PLT variant (`plt_num_loops=2`). In the accompanying paper, this setting gives the best gain-cost trade-off: the second loop provides most of the useful latent refinement, while additional loops show diminishing or unstable updates.
 ## Highlights
@@ -118,9 +120,13 @@ LoopCoder-v2 can produce incorrect, insecure, or incomplete code and should not
 ## Citation
 ```bibtex
-@misc{loopcoder_v2_2026,
-  title = {LoopCoder-v2: Only Loop Once for Efficient Test-Time Computation Scaling},
-  author = {Yang, Jian and Guo, Shawn and Zhang, Wei and Zheng, Tianyu and Du, Yaxin and Li, Haau-Sing and Wu, Jiajun and Song, Yue and Xing, Yan and Cai, Qingsong and Huang, Zelong and Hao, Chuan and Tao, Ran and Liu, Xianglong and Zhao, Wayne Xin and Tang, Mingjie and Lv, Weifeng and Zhou, Ming and Dai, Bryan},
-  year = {2026}
 }
-```

 ---
 library_name: transformers
+license: apache-2.0
 pipeline_tag: text-generation
 tags:
 - code
 # LoopCoder-V2
+[**Paper**](https://huggingface.co/papers/2606.18023) | [**GitHub**](https://github.com/CSJianYang/LoopCoder)
 LoopCoder-v2 is a 7B instruction-tuned code model based on the Parallel Loop Transformer (PLT). The model studies test-time computation scaling through repeated application of shared Transformer blocks while keeping the parameter count fixed.
+The released checkpoint is the two-loop PLT variant (`plt_num_loops=2`). In the accompanying paper, [LoopCoder-v2: Only Loop Once for Efficient Test-Time Computation Scaling](https://huggingface.co/papers/2606.18023), this setting gives the best gain-cost trade-off: the second loop provides most of the useful latent refinement, while additional loops show diminishing or unstable updates.
 ## Highlights
 ## Citation
 ```bibtex
+@misc{yang2026loopcoderv2loopefficienttesttime,
+      title={LoopCoder-v2: Only Loop Once for Efficient Test-Time Computation Scaling},
+      author={Jian Yang and Shawn Guo and Wei Zhang and Tianyu Zheng and Yaxin Du and Haau-Sing Li and Jiajun Wu and Yue Song and Yan Xing and Qingsong Cai and Zelong Huang and Chuan Hao and Ran Tao and Xianglong Liu and Wayne Xin Zhao and Mingjie Tang and Weifeng Lv and Ming Zhou and Bryan Dai},
+      year={2026},
+      eprint={2606.18023},
+      archivePrefix={arXiv},
+      primaryClass={cs.LG},
+      url={https://arxiv.org/abs/2606.18023},
 }
+```