Update README.md
Browse files
README.md
CHANGED
@@ -35,11 +35,11 @@ Zephyr is a series of language models that are trained to act as helpful assista
|
|
35 |
<!-- Provide the basic links for the model. -->
|
36 |
|
37 |
- **Repository:** https://github.com/huggingface/alignment-handbook
|
38 |
-
- **Demo:** https://huggingface.co/spaces/HuggingFaceH4/zephyr-
|
39 |
|
40 |
## Intended uses & limitations
|
41 |
|
42 |
-
The model was initially fine-tuned on a variant of the [`UltraChat`](https://huggingface.co/datasets/stingning/ultrachat) dataset, which contains a diverse range of synthetic dialogues generated by ChatGPT. We then further aligned the model with [🤗 TRL's](https://github.com/huggingface/trl) `DPOTrainer` on the [openbmb/UltraFeedback](https://huggingface.co/datasets/openbmb/UltraFeedback) dataset, which contain 64k prompts and model completions that are ranked by GPT-4. As a result, the model can be used for chat and you can check out our [demo](https://huggingface.co/spaces/HuggingFaceH4/zephyr-
|
43 |
|
44 |
Here's how you can run the model using the `pipeline()` function from 🤗 Transformers:
|
45 |
|
|
|
35 |
<!-- Provide the basic links for the model. -->
|
36 |
|
37 |
- **Repository:** https://github.com/huggingface/alignment-handbook
|
38 |
+
- **Demo:** https://huggingface.co/spaces/HuggingFaceH4/zephyr-chat
|
39 |
|
40 |
## Intended uses & limitations
|
41 |
|
42 |
+
The model was initially fine-tuned on a variant of the [`UltraChat`](https://huggingface.co/datasets/stingning/ultrachat) dataset, which contains a diverse range of synthetic dialogues generated by ChatGPT. We then further aligned the model with [🤗 TRL's](https://github.com/huggingface/trl) `DPOTrainer` on the [openbmb/UltraFeedback](https://huggingface.co/datasets/openbmb/UltraFeedback) dataset, which contain 64k prompts and model completions that are ranked by GPT-4. As a result, the model can be used for chat and you can check out our [demo](https://huggingface.co/spaces/HuggingFaceH4/zephyr-chat) to test its capabilities.
|
43 |
|
44 |
Here's how you can run the model using the `pipeline()` function from 🤗 Transformers:
|
45 |
|