Improve model card with metadata and links
Browse filesThis PR improves the model card by adding missing metadata, including the `pipeline_tag` and `library_name`. It also clarifies the license and includes a link to the project page. This improves the discoverability and usability of the model.
README.md
CHANGED
|
@@ -1,3 +1,11 @@
|
|
| 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 dataset contains 36k high-quality preference comparison pairs aligned with the preferences of professional psychotherapists.
|
| 8 |
+
|
| 9 |
+
The model aims to improve the quality of responses in psycho-counseling sessions and achieves a win rate of 87% against GPT-4o.
|
| 10 |
+
|
| 11 |
+
Project page: https://hf.co/Psychotherapy-LLM
|