19 lines
455 B
Markdown
19 lines
455 B
Markdown
|
---
|
||
|
|
language:
|
||
|
|
- ko
|
||
|
|
- en
|
||
|
|
license: mit
|
||
|
|
---
|
||
|
|
|
||
|
|
# Model Card for free-llama-dpo-v0.2
|
||
|
|
|
||
|
|
## Developed by : [Freewheelin](https://freewheelin-recruit.oopy.io/) AI Technical Team
|
||
|
|
|
||
|
|
## Hardware and Software
|
||
|
|
|
||
|
|
* **Training Factors**: We fine-tuned this model using the [HuggingFace TRL Trainer](https://huggingface.co/docs/trl/trainer)
|
||
|
|
|
||
|
|
## Method
|
||
|
|
- This model was trained using the learning method introduced in the [SOLAR paper](https://arxiv.org/pdf/2312.15166.pdf).
|
||
|
|
|