Add pipeline tag and link to Github repository
Browse filesThis PR adds the `pipeline_tag: text-generation` to the metadata so the model can be found at https://huggingface.co/models?pipeline_tag=text-generation. It also adds a link to the Github repository for easier access to the code.
README.md
CHANGED
|
@@ -1,15 +1,19 @@
|
|
| 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.
|
| 12 |
|
|
|
|
|
|
|
| 13 |
## Links to Other Models
|
| 14 |
- [Zephyr-7B-DICE-Iter1](https://huggingface.co/sail/Zephyr-7B-DICE-Iter1)
|
| 15 |
- [Zephyr-7B-DICE-Iter2](https://huggingface.co/sail/Zephyr-7B-DICE-Iter2)
|
|
|
|
| 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.
|
| 14 |
|
| 15 |
+
Code: https://github.com/sail-sg/dice
|
| 16 |
+
|
| 17 |
## Links to Other Models
|
| 18 |
- [Zephyr-7B-DICE-Iter1](https://huggingface.co/sail/Zephyr-7B-DICE-Iter1)
|
| 19 |
- [Zephyr-7B-DICE-Iter2](https://huggingface.co/sail/Zephyr-7B-DICE-Iter2)
|