|
|
--- |
|
|
base_model: Shekswess/tiny-think-sft-math-stem-loss-nll-bf16-lr2e-5-e2-bs8 |
|
|
library_name: transformers |
|
|
model_name: tiny-think-dpo-math-stem-apo_zero-beta1-lr3e-6-e1-bs8 |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
- dpo |
|
|
- trl |
|
|
licence: license |
|
|
--- |
|
|
|
|
|
# Model Card for tiny-think-dpo-math-stem-apo_zero-beta1-lr3e-6-e1-bs8 |
|
|
|
|
|
This model is a fine-tuned version of [Shekswess/tiny-think-sft-math-stem-loss-nll-bf16-lr2e-5-e2-bs8](https://huggingface.co/Shekswess/tiny-think-sft-math-stem-loss-nll-bf16-lr2e-5-e2-bs8). |
|
|
It has been trained using [TRL](https://github.com/huggingface/trl). |
|
|
|
|
|
## Training procedure |
|
|
|
|
|
This model was trained with DPO, a method introduced in [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://huggingface.co/papers/2305.18290). |
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- TRL: 0.26.2 |
|
|
- Transformers: 4.57.5 |
|
|
- Pytorch: 2.9.0+cu128 |
|
|
- Datasets: 4.5.0 |
|
|
- Tokenizers: 0.22.2 |
