Downloads · 30 days
22
4% of all-time downloads
phi-2-dpo-pairs
rhysjones/phi-2-dpo-pairs
phi-2-dpo-pairs is a text generation model from rhysjones. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as mit.
This is a test DPO finetune of Microsoft phi-2
All-time downloads
498
Public
Parameters
2.8B
5.6 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors5.6 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- mit
- Model type
- phi-msft
- Access
- Public
- Created
- Jan 7, 2024
- Updated
- Jan 8, 2024
- SHA
- 421d32c4
Try a prompt
Model card
From the Hugging Face model README
This is a test DPO finetune of Microsoft phi-2
Two DPO datasets are used. Training was for 1 epoch as a qlora with rank 64.
Initial Evals
- ARC: 63.14
- TruthfulQA: 48.47
- Task
- Text Generation
- Library
- transformers
- Type
- phi-msft
- License
- mit
- Created
- Jan 7, 2024
- Updated
- Jan 8, 2024