Add pipeline tag and link to Github repository (#1)
Browse files- Add pipeline tag and link to Github repository (b2cc1fb07ad79a789f61c32d76cdee4c9fea213b)
- Update README.md (75daac7f44d364e7bca45b7d2dfcb617587f073a)
Co-authored-by: Niels Rogge <[email protected]>
README.md
CHANGED
|
@@ -1,11 +1,13 @@
|
|
| 1 |
---
|
| 2 |
-
library_name: transformers
|
| 3 |
-
license: mit
|
| 4 |
datasets:
|
| 5 |
- HuggingFaceH4/ultrafeedback_binarized
|
| 6 |
language:
|
| 7 |
- en
|
|
|
|
|
|
|
|
|
|
| 8 |
---
|
|
|
|
| 9 |
# Zephyr-7B-DICE-Iter2
|
| 10 |
|
| 11 |
This model was developed using [Bootstrapping Language Models with DPO Implicit Rewards](https://arxiv.org/abs/2406.09760) (DICE) at iteration 2, based on the [HuggingFaceH4/zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta) as the starting point.
|
|
@@ -29,6 +31,9 @@ This model was developed using [Bootstrapping Language Models with DPO Implicit
|
|
| 29 |
|[Zephyr-7B-DICE-Iter1](https://huggingface.co/sail/Zephyr-7B-DICE-Iter1) |19.03 |17.67
|
| 30 |
|[Zephyr-7B-DICE-Iter2](https://huggingface.co/sail/Zephyr-7B-DICE-Iter2) |**20.71** |**20.16**
|
| 31 |
|
|
|
|
|
|
|
|
|
|
| 32 |
## Citation
|
| 33 |
|
| 34 |
```bibtex
|
|
|
|
| 1 |
---
|
|
|
|
|
|
|
| 2 |
datasets:
|
| 3 |
- HuggingFaceH4/ultrafeedback_binarized
|
| 4 |
language:
|
| 5 |
- en
|
| 6 |
+
library_name: transformers
|
| 7 |
+
license: mit
|
| 8 |
+
pipeline_tag: text-generation
|
| 9 |
---
|
| 10 |
+
|
| 11 |
# Zephyr-7B-DICE-Iter2
|
| 12 |
|
| 13 |
This model was developed using [Bootstrapping Language Models with DPO Implicit Rewards](https://arxiv.org/abs/2406.09760) (DICE) at iteration 2, based on the [HuggingFaceH4/zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta) as the starting point.
|
|
|
|
| 31 |
|[Zephyr-7B-DICE-Iter1](https://huggingface.co/sail/Zephyr-7B-DICE-Iter1) |19.03 |17.67
|
| 32 |
|[Zephyr-7B-DICE-Iter2](https://huggingface.co/sail/Zephyr-7B-DICE-Iter2) |**20.71** |**20.16**
|
| 33 |
|
| 34 |
+
## Code
|
| 35 |
+
https://github.com/sail-sg/dice
|
| 36 |
+
|
| 37 |
## Citation
|
| 38 |
|
| 39 |
```bibtex
|