Instructions to use JingyaoLi/MoTCoder-7B-v1.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use JingyaoLi/MoTCoder-7B-v1.5 with Transformers:

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

pipe = pipeline("text-generation", model="JingyaoLi/MoTCoder-7B-v1.5")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("JingyaoLi/MoTCoder-7B-v1.5")
model = AutoModelForCausalLM.from_pretrained("JingyaoLi/MoTCoder-7B-v1.5")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use JingyaoLi/MoTCoder-7B-v1.5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "JingyaoLi/MoTCoder-7B-v1.5"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "JingyaoLi/MoTCoder-7B-v1.5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/JingyaoLi/MoTCoder-7B-v1.5

SGLang

How to use JingyaoLi/MoTCoder-7B-v1.5 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 "JingyaoLi/MoTCoder-7B-v1.5" \
    --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": "JingyaoLi/MoTCoder-7B-v1.5",
		"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 "JingyaoLi/MoTCoder-7B-v1.5" \
        --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": "JingyaoLi/MoTCoder-7B-v1.5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use JingyaoLi/MoTCoder-7B-v1.5 with Docker Model Runner:
```
docker model run hf.co/JingyaoLi/MoTCoder-7B-v1.5
```

🏠 MoTCoder

• 🤗 Data • 🤗 MoTCoder-32B • 🤗 MoTCoder-7B • 🐱 Code • 📃 Paper

Large Language Models (LLMs) have showcased impressive capabilities in handling straightforward programming tasks. However, their performance tends to falter when confronted with more challenging programming problems. We observe that conventional models often generate solutions as monolithic code blocks, restricting their effectiveness in tackling intricate questions. To overcome this limitation, we present Module-of-Thought Coder (MoTCoder). We introduce a framework for MoT instruction tuning, designed to promote the decomposition of tasks into logical sub-tasks and sub-modules. Our investigations reveal that, through the cultivation and utilization of sub-modules, MoTCoder significantly improves both the modularity and correctness of the generated solutions, leading to substantial pass@1 improvements of 5.8% on APPS and 5.9% on CodeContests. MoTCoder also achieved significant improvements in self-correction capabilities, surpassing the current SOTA by 3.3%. Additionally, we provide an analysis of between problem complexity and optimal module decomposition and evaluate the maintainability index, confirming that the code generated by MoTCoder is easier to understand and modify, which can be beneficial for long-term code maintenance and evolution. Our codes are available at https://github.com/dvlab-research/MoTCoder.

Performance

APPS

CodeContests

Reflection

Citation

If you find our work useful, please consider citing it.

@misc{li2025motcoderelevatinglargelanguage,
      title={MoTCoder: Elevating Large Language Models with Modular of Thought for Challenging Programming Tasks}, 
      author={Jingyao Li and Pengguang Chen and Bin Xia and Hong Xu and Jiaya Jia},
      year={2025},
      eprint={2312.15960},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/2312.15960}, 
}

Downloads last month: 5

Safetensors

Model size

8B params

Tensor type

BF16

Paper for JingyaoLi/MoTCoder-7B-v1.5

MoTCoder: Elevating Large Language Models with Modular of Thought for Challenging Programming Tasks

Paper • 2312.15960 • Published Dec 26, 2023 • 1