Modelpublic

Delta-Vector/MS3.2-Austral-24B-KTO

sourceHugging Faceupdated 1y agoView on Hugging Face

0likes13downloads

Model Card

What is this

This the KTO checkpoint of my MS3.2 Austral winton train. Use the MS3.2 Winton train for the best experience.

wandb: https://wandb.ai/new-eden/austral/runs/2iaj6moy?nw=nwuserdeltavector

Datasets:

datasets:
  - path: Delta-Vector/Tauri-IFeval-Dans-Tulu-KTO
    split: train
    type: chatml.argilla
  - path: Delta-Vector/Tauri-Opus-accepted-hermes-rejected-shuffled 
    split: train
    type: chatml.argilla
  - path: Delta-Vector/Tauri-Opus-Accepted-GPT-Rejected-Opus-Writing-Prompts
    split: train
    type: chatml.argilla
  - path: Delta-Vector/Tauri-Helpsteer3-Edit
    split: train
    type: chatml.argilla
  - path: Delta-Vector/Tauri-Helpsteer-3-Preference-KTO
    split: train
    type: chatml.argilla
  - path: NewEden/Purpura-Arkhaios-CC-KTO
    split: train
    type: chatml.argilla
  - path: Delta-Vector/Tauri-KTO-Instruct-Mix
    split: train
    type: chatml.argilla
  - path: Delta-Vector/Tauri-LIT-RL-KTO
    split: train
    type: chatml.argilla
  - path: Delta-Vector/Tauri-Synth-1-KTO-R1-No-Think
    split: train
    type: chatml.argilla

Trained on 8xA100s using Axolotl. Ty to my work & Auri <3