Quantization made by Richard Erkhov.
This model is for WASSA2024 Track 1,2,3. It is fine-tuned on LLama3-8B-instrcut using standard prediction, role-play, and contrastive supervised fine-tune template. The learning rate for this model is 8e-5.
This repository's models are open-sourced under the Apache-2.0 license, and their weight usage must adhere to LLama3
MODEL LICENCE license.
