Improve model card: Add metadata, paper link, and project page
Browse filesThis PR improves the model card by:
- Adding the `pipeline_tag` (`text-generation`), making the model discoverable via https://huggingface.co/models?pipeline_tag=text-generation.
- Adding the `library_name` (`transformers`).
- Linking the model to its paper.
- Adding a brief description of the model and its purpose.
- Linking to the project page, where users can find the dataset and reward model.
README.md
CHANGED
|
@@ -1,3 +1,9 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: llama3.1
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: llama3.1
|
| 3 |
+
library_name: transformers
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
---
|
| 6 |
+
|
| 7 |
+
This model, PsychoCounsel-Llama3-8B, was presented in the paper [Preference Learning Unlocks LLMs' Psycho-Counseling Skills](https://hf.co/papers/2502.19731). It's a fine-tuned Llama 3 model trained using preference learning on the PsychoCounsel-Preference dataset. This model achieves an impressive win rate of 87% against GPT-4o in psycho-counseling tasks.
|
| 8 |
+
|
| 9 |
+
The model, along with the dataset and reward model, are available at the project page: [https://hf.co/Psychotherapy-LLM](https://hf.co/Psychotherapy-LLM).
|