metadata
license: llama3.1
library_name: transformers
pipeline_tag: text-generation
This model, PsychoCounsel-Llama3-8B, was presented in the paper Preference Learning Unlocks LLMs' Psycho-Counseling Skills. 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.
The model aims to improve the quality of responses in psycho-counseling sessions and achieves a win rate of 87% against GPT-4o.
Project page: https://hf.co/Psychotherapy-LLM