CodeI/O: Condensing Reasoning Patterns via Code Input-Output Prediction

📑 Paper    |    🌐 Project Page    |    💾 Released Resources    |    📦 Repo

This is the resource page of the CodeI/O collection on Huggingface, we highlight your currect position with a blue block.

Dataset

Dataset Link
PythonEdu Link

Models

Base Model / Training CodeI/O CodeI/O++
Stage 1 Stage 2 Stage 1 Stage 2
Qwen 2.5 7B Coder Link Link Link Link
LLaMA 3.1 8B Link Link Link Link
DeepSeek v2 Lite Coder Link Link Link Link

Citation

If you find these resources helpful, please kindly cite as:

TBD
Downloads last month
0
Safetensors
Model size
7.62B params
Tensor type
BF16
·
Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and HF Inference API was unable to determine this model's library.

Collection including hkust-nlp/qwen2.5-7b-coder_codeio_stage1