nbeerbower/llama-3-stella-truthy-dpo-8B
Text Generation
•
Updated
•
730
llama 3 experiments
Merge and finetune experiments with llama 3, aiming for decensorship and benchmark performance.
-
-
nbeerbower/llama-3-stella-8B
Text Generation • Updated • 745 • 1 -
nbeerbower/llama-3-bible-dpo-8B
Text Generation • Updated • 3 • 1 -
nbeerbower/llama-3-wissenschaft-8B-v2
Text Generation • Updated • 1.17k • 1 -
nbeerbower/llama-3-gutenberg-8B
Text Generation • Updated • 2.02k • 2 -
nbeerbower/llama-3-dragonmaid-8B-v2
Text Generation • Updated • 1.93k • 1 -
nbeerbower/llama-3-stinky-8B
Text Generation • Updated • 1.13k • 2 -
nbeerbower/llama-3-bophades-v3-8B
Text Generation • Updated • 394 • 1 -
nbeerbower/llama-3-wissenschaft-8B
Text Generation • Updated • 1.36k • 2 -
nbeerbower/llama-3-slerp-kraut-dragon-8B
Text Generation • Updated • 1.46k • 1 -
nbeerbower/llama-3-dragonmaid-8B
Text Generation • Updated • 23 -
nbeerbower/llama-3-dragon-bophades-8B
Text Generation • Updated • 75 • 4 -
nbeerbower/llama-3-aura-bophades-8B
Text Generation • Updated • 13 • 1 -
nbeerbower/llama-3-bophades-v2-8B
Text Generation • Updated • 1.41k • 3 -
nbeerbower/llama-3-slerp-dolphin-sauce-8B
Text Generation • Updated • 9 -
nbeerbower/llama-3-sauce-v1-8B
Text Generation • Updated • 15 • 1 -
nbeerbower/llama-3-bophades-v1-8B
Text Generation • Updated • 30 • 2