KTO checkpoint of my GLM4 train, use the down-stream version -Winton

Delta-Vector/Tauri-IF-AM-Thinking
Delta-Vector/Tauri-KTO-Instruct-mix-v3
Delta-Vector/Tauri-LIT-RL-KTO
Delta-Vector/Tauri-Helpsteer3-Edit
Delta-Vector/Tauri-Physical-Reasoning
Delta-Vector/Tauri-Helpsteer-3-Preference-KTO
Delta-Vector/Tauri-Opus-Accepted-GPT-Rejected-Opus-Writing-Prompts
Delta-Vector/Tauri-KTO-Instruct-Mix
Delta-Vector/Tauri-Purpura-Arkhaios-CC-KTO
Delta-Vector/Tauri-Opus-accepted-hermes-rejected-shuffled
Delta-Vector/Tauri-Helpsteer3-Edit

datasets used are above:

wandb: https://wandb.ai/new-eden/Austral-32B/runs/r8fnw6t9?nw=nwuserdeltavector

Downloads last month
179
Safetensors
Model size
32.6B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Delta-Vector/Austral-GLM4-KTO

Finetuned
(1)
this model
Finetunes
1 model
Quantizations
2 models

Datasets used to train Delta-Vector/Austral-GLM4-KTO