|
--- |
|
license: apache-2.0 |
|
language: |
|
- en |
|
base_model: |
|
- meta-llama/Meta-Llama-3.1-8B |
|
--- |
|
|
|
# Empathetic teacher model |
|
|
|
## Overview |
|
|
|
This is a LLM fine-tuned with real-life, ideally-empathetic teacher-student conversations. |
|
This model processes the recent conversation history and provides guidance on how a teacher might respond to the student's utterance. |
|
|
|
To fine-tune an open-weighted LLM to act as this generic teacher, we are using the following datasets: |
|
the Teacher-Student Chatroom Corpus, |
|
TSCCv2 [Caines et al., 2022](https://aclanthology.org/2022.nlp4call-1.3), |
|
CIMA [Stasaski et al., 2020](https://aclanthology.org/2020.bea-1.5), |
|
the Multicultural Classroom Discourse Dataset [Rapanta et al., 2021](https://www.sciencedirect.com/science/article/pii/S2352340921007940), |
|
MathDial [Macina et al., 2023](https://aclanthology.org/2023.findings-emnlp.372), and |
|
Conversational Uptake [Demszky et al., 2021]. |
|
|
|
We are evaluating LLaMa-3, Phi-3, and Gemma-2 for this task. |
|
Instead of using programmable fine-tuning libraries such as Axolotl ([link](https://github.com/OpenAccess-AI-Collective/axolotl)) |
|
or Huggingface TRL ([link](https://github.com/huggingface/trl)), |
|
we are employing the more general command-line LLaMA-Factory ([link](https://github.com/hiyouga/LLaMA-Factory)) toolkit |
|
that facilitates the fine-tuning of various well-known LLMs on custom data. |
|
Parameter-efficient fine-tuning is achieved via the QLoRA method [Dettmers et al., 2023](https://proceedings.neurips.cc/paper_files/paper/2023/file/1feb87871436031bdc0f2beaa62a049b-Paper-Conference.pdf). |
|
|
