Add model card, link to paper

#1
by nielsr HF staff - opened
Files changed (1) hide show
  1. README.md +5 -67
README.md CHANGED
@@ -1,73 +1,11 @@
1
  ---
2
- # For reference on dataset card metadata, see the spec: https://github.com/huggingface/hub-docs/blob/main/datasetcard.md?plain=1
3
- # Doc / guide: https://huggingface.co/docs/hub/datasets-cards
4
- {}
5
  ---
6
 
7
  # CodeI/O: Condensing Reasoning Patterns via Code Input-Output Prediction
8
 
9
- <p align="left">
10
- 📑 <a href="https://huggingface.co/papers/2502.07316" target="_blank">Paper</a> &nbsp&nbsp | &nbsp&nbsp 🌐 <a href="https://codei-o.github.io/" target="_blank">Project Page</a> &nbsp&nbsp | &nbsp&nbsp 💾 <a href="https://huggingface.co/collections/hkust-nlp/codei-o-67a978e28fd926b56a4f55a2" target="_blank">Released Resources</a> &nbsp&nbsp | &nbsp&nbsp 📦 <a href="https://github.com/hkust-nlp/CodeIO" target="_blank">Repo</a>
11
 
12
- This is the resource page of the CodeI/O collection on Huggingface, we highlight your currect position with a blue block.
13
-
14
- **Dataset**
15
- <table>
16
- <tr>
17
- <th>Dataset</th>
18
- <th>Link</th>
19
- </tr>
20
- <tr>
21
- <td>CodeI/O-PythonEdu-Reasoning</td>
22
- <td style="text-align: center; vertical-align: middle;">
23
- <a href="https://huggingface.co/datasets/hkust-nlp/CodeIO-PyEdu-Reasoning">🤗</a>
24
- </td>
25
- </tr>
26
- </table>
27
-
28
- **Models**
29
- <table>
30
- <tr>
31
- <th rowspan="2">Base Model / Training</th>
32
- <th colspan="2">CodeI/O</th>
33
- <th colspan="2">CodeI/O++</th>
34
- </tr>
35
- <tr>
36
- <th>Stage 1</th>
37
- <th>Stage 2</th>
38
- <th>Stage 1</th>
39
- <th>Stage 2</th>
40
- </tr>
41
- <tr>
42
- <td>Qwen 2.5 7B Coder</td>
43
- <td style="text-align: center; vertical-align: middle;"><a href="https://huggingface.co/hkust-nlp/qwen2.5-7b-coder_codeio_stage1">🤗</a></td>
44
- <td style="background-color: #e6f3ff; text-align: center; vertical-align: middle;"><a href="https://huggingface.co/hkust-nlp/qwen2.5-7b-coder_codeio">🤗</a></td>
45
- <td style="text-align: center; vertical-align: middle;"><a href="https://huggingface.co/hkust-nlp/qwen2.5-7b-coder_codeio_pp_stage1">🤗</a></td>
46
- <td style="text-align: center; vertical-align: middle;"><a href="https://huggingface.co/hkust-nlp/qwen2.5-7b-coder_codeio_pp">🤗</a></td>
47
- </tr>
48
- <tr>
49
- <td>LLaMA 3.1 8B</td>
50
- <td style="text-align: center; vertical-align: middle;"><a href="https://huggingface.co/hkust-nlp/llama3.1-8b_codeio_stage1">🤗</a></td>
51
- <td style="text-align: center; vertical-align: middle;"><a href="https://huggingface.co/hkust-nlp/llama3.1-8b_codeio">🤗</a></td>
52
- <td style="text-align: center; vertical-align: middle;"><a href="https://huggingface.co/hkust-nlp/llama3.1-8b_codeio_pp_stage1">🤗</a></td>
53
- <td style="text-align: center; vertical-align: middle;"><a href="https://huggingface.co/hkust-nlp/llama3.1-8b_codeio_pp">🤗</a></td>
54
- </tr>
55
- <tr>
56
- <td>DeepSeek v2 Lite Coder</td>
57
- <td style="text-align: center; vertical-align: middle;"><a href="https://huggingface.co/hkust-nlp/dsv2-lite-coder_codeio_stage1">🤗</a></td>
58
- <td style="text-align: center; vertical-align: middle;"><a href="https://huggingface.co/hkust-nlp/dsv2-lite-coder_codeio">🤗</a></td>
59
- <td style="text-align: center; vertical-align: middle;"><a href="https://huggingface.co/hkust-nlp/dsv2-lite-coder_codeio_pp_stage1">🤗</a></td>
60
- <td style="text-align: center; vertical-align: middle;"><a href="https://huggingface.co/hkust-nlp/dsv2-lite-coder_codeio_pp">🤗</a></td>
61
- </tr>
62
- </table>
63
-
64
- ## Citation
65
- If you find these resources helpful, please kindly cite as:
66
- ```
67
- @article{li2025codeio,
68
- title={CodeI/O: Condensing Reasoning Patterns via Code Input-Output Prediction},
69
- author={Li, Junlong and Guo, Daya and Yang, Dejian and Xu, Runxin and Wu, Yu and He, Junxian},
70
- journal={arXiv preprint arXiv:2502.07316},
71
- year={2025}
72
- }
73
- ```
 
1
  ---
2
+ library_name: transformers
3
+ pipeline_tag: text-generation
4
+ license: mit
5
  ---
6
 
7
  # CodeI/O: Condensing Reasoning Patterns via Code Input-Output Prediction
8
 
9
+ This repository contains the models described in [CodeI/O: Condensing Reasoning Patterns via Code Input-Output Prediction](https://huggingface.co/papers/2502.07316).
 
10
 
11
+ Code: https://github.com/hkust-nlp/CodeIO