Instructions to use jeonghuncho/CoCoS-Llama-3.2-1B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jeonghuncho/CoCoS-Llama-3.2-1B with Transformers:

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

pipe = pipeline("text-generation", model="jeonghuncho/CoCoS-Llama-3.2-1B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("jeonghuncho/CoCoS-Llama-3.2-1B")
model = AutoModelForCausalLM.from_pretrained("jeonghuncho/CoCoS-Llama-3.2-1B")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use jeonghuncho/CoCoS-Llama-3.2-1B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jeonghuncho/CoCoS-Llama-3.2-1B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jeonghuncho/CoCoS-Llama-3.2-1B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/jeonghuncho/CoCoS-Llama-3.2-1B

SGLang

How to use jeonghuncho/CoCoS-Llama-3.2-1B 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 "jeonghuncho/CoCoS-Llama-3.2-1B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jeonghuncho/CoCoS-Llama-3.2-1B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "jeonghuncho/CoCoS-Llama-3.2-1B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jeonghuncho/CoCoS-Llama-3.2-1B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use jeonghuncho/CoCoS-Llama-3.2-1B with Docker Model Runner:
```
docker model run hf.co/jeonghuncho/CoCoS-Llama-3.2-1B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Citation [optional]

BibTeX:

@misc{cho2025selfcorrectingcodegenerationusing,
      title={Self-Correcting Code Generation Using Small Language Models}, 
      author={Jeonghun Cho and Deokhyung Kang and Hyounghun Kim and Gary Geunbae Lee},
      year={2025},
      eprint={2505.23060},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2505.23060}, 
}

Downloads last month: 8

Safetensors

Model size

1B params

Tensor type

BF16

Model tree for jeonghuncho/CoCoS-Llama-3.2-1B

Quantizations

1 model

Paper for jeonghuncho/CoCoS-Llama-3.2-1B

Self-Correcting Code Generation Using Small Language Models

Paper • 2505.23060 • Published May 29, 2025 • 1