Skip to content

Commit

Permalink
Update README.md
Browse files Browse the repository at this point in the history
  • Loading branch information
kazemnejad authored Oct 2, 2024
1 parent 6b2c914 commit ccae82a
Showing 1 changed file with 5 additions and 0 deletions.
5 changes: 5 additions & 0 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -10,6 +10,7 @@
- [Running the experiments](#running-the-experiments)
- [Code Structure](#code-structure)
- [Initial SFT Checkpoints](#initial-sft-checkpoints)
- [Acknowledgement](#acknowledgement)
- [Citation](#citation)


Expand Down Expand Up @@ -153,6 +154,10 @@ singularity exec --nv \
| DeepSeekMath | [🤗 Deepseekmath-SFT-GSM8K](https://huggingface.co/realtreetune/deepseekmath-7b-sft-GSM8K) | [🤗 Deepseekmath-SFT-MATH](https://huggingface.co/realtreetune/deepseekmath-7b-sft-MATH-v2) |
| Rho1B | [🤗 Rhomath-SFT-GSM8K](https://huggingface.co/realtreetune/rho-1b-sft-GSM8K) | [🤗 Rhomath-SFT-MATH](https://huggingface.co/realtreetune/rho-1b-sft-MATH) |

## Acknowledgement

This is the release codebase for VinePPO. It is developed by [@kazemnejad](https://github.com/kazemnejad) and [@miladink](https://github.com/miladink).

## Code Structure
- [`configs`](https://github.com/McGill-NLP/vineppo/tree/main/configs): Contains Jsonnet files for configuring experiment settings.
- [`src/treetune`](https://github.com/McGill-NLP/vineppo/tree/main/src/treetune): The main directory for source code, encompassing:
Expand Down

0 comments on commit ccae82a

Please sign in to comment.