dpo/sft tuned language models on politune
Jonas Golde
whoisjones
AI & ML interests
Data-efficient transfer learning
Recent Activity
updated a collection about 7 hours ago
Politune updated a collection about 7 hours ago
Politune updated a collection about 7 hours ago
PolituneOrganizations
models 24
whoisjones/politune-qwen3-8b-right-dpo
Text Generation • Updated
whoisjones/politune-qwen3-8b-right-sft
Text Generation • Updated
whoisjones/politune-qwen3-8b-left-dpo
Text Generation • Updated
whoisjones/politune-qwen3-8b-left-sft
Text Generation • Updated
whoisjones/politune-mistral-7b-right-dpo
Text Generation • Updated
whoisjones/politune-mistral-7b-right-sft
Text Generation • Updated
whoisjones/politune-mistral-7b-left-dpo
Text Generation • Updated
whoisjones/politune-mistral-7b-left-sft
Text Generation • Updated
whoisjones/politune-llama3-8b-right-dpo
Text Generation • Updated
whoisjones/politune-llama3-8b-right-sft
Text Generation • Updated
datasets 29
whoisjones/finerweb_document_context
Updated • 6
whoisjones/sudoku
Viewer • Updated • 1.42M • 16
whoisjones/maze
Viewer • Updated • 9k • 7
whoisjones/multinerd
Viewer • Updated • 1.67M • 35
whoisjones/masakhaner
Viewer • Updated • 153k • 10 • 1
whoisjones/uner
Viewer • Updated • 66.8k • 53
whoisjones/fiNERweb
Viewer • Updated • 3.98M • 150 • 9
whoisjones/fiNERweb-x
Updated • 31
whoisjones/fiNERweb-x-multi
Updated • 29
whoisjones/fiNERweb-gemma-x-multi
Updated • 13