Downloads · 30 days
4
10% of all-time downloads
dpo-mistral-7b-ultrafeedback-binarized-preferences-cleaned-v0.2
dteome/dpo-mistral-7b-ultrafeedback-binarized-preferences-cleaned-v0.2
dpo-mistral-7b-ultrafeedback-binarized-preferences-cleaned-v0.2 is a text generation model from dteome. 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.
DPO training of Mistral-7B-Instruct-v0.2 using the fixed and cleaned UltraFeedback dataset argilla/ultrafeedback-binarized-preferences-cleaned
All-time downloads
39
Public
Parameters
7.2B
14.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors14.5 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- mit
- Model type
- mistral
- Access
- Public
- Created
- Mar 12, 2024
- Updated
- Mar 12, 2024
- SHA
- 289eaf96
Try a prompt
Model card
From the Hugging Face model README
Mistral-7B-ultrafeedback-binarized-preferences-cleaned-v0.2
DPO training of Mistral-7B-Instruct-v0.2 using the fixed and cleaned UltraFeedback dataset argilla/ultrafeedback-binarized-preferences-cleaned
MT-Bench evalution
Pairwise comparison with gpt-4-turbo-preview
| model | win | loss | tie | win_rate | loss_rate | win_rate_adjusted |
|---|---|---|---|---|---|---|
| mistral-7b-instruct-v0.2-ultrafeedback | 61 | 20 | 79 | 0.38125 | 0.12500 | 0.628125 |
| mistral-7b-instruct-v0.2 | 20 | 61 | 79 | 0.12500 | 0.38125 | 0.371875 |
- Task
- Text Generation
- Library
- transformers
- Type
- mistral
- License
- mit
- Created
- Mar 12, 2024
- Updated
- Mar 12, 2024