GRPO/PPO Finetunes for Creative Writing
DV
Delta-Vector
AI & ML interests
Post training @ https://dphn.ai
Recent Activity
updated
a dataset 1 day ago
NewEden/test-cai published
a dataset 1 day ago
NewEden/test-cai updated
a dataset 5 days ago
Delta-Vector/CAI-critic-revision-8k-cleaned-sharegpt Organizations
Got bored - Did a weird tune on harbinger and now there's 10K of these, Models meant for Adventure/RP, Creative and smartz.
-
Delta-Vector/Austral-70B-Winton
Text Generation • 71B • Updated • 15 • • 6 -
Delta-Vector/Austral-32B-GLM4-Winton
Text Generation • 33B • Updated • 14 • 8 -
Delta-Vector/MS3.2-Austral-Winton
Text Generation • 24B • Updated • 58 • 12 -
Delta-Vector/Austral-24B-Winton
Text Generation • 24B • Updated • 59 • 14
GRPO/PPO Finetunes for Creative Writing
Got bored - Did a weird tune on harbinger and now there's 10K of these, Models meant for Adventure/RP, Creative and smartz.
-
Delta-Vector/Austral-70B-Winton
Text Generation • 71B • Updated • 15 • • 6 -
Delta-Vector/Austral-32B-GLM4-Winton
Text Generation • 33B • Updated • 14 • 8 -
Delta-Vector/MS3.2-Austral-Winton
Text Generation • 24B • Updated • 58 • 12 -
Delta-Vector/Austral-24B-Winton
Text Generation • 24B • Updated • 59 • 14
models 181
Delta-Vector/results_2026-02-22T07-08-25.244194.json
Updated
Delta-Vector/results_2026-01-16T09-25-13.279216.json
Updated
Delta-Vector/results_2026-02-10T03-17-43.281923.json
Updated
Delta-Vector/results_2026-02-10T00-54-57.491762.json
Updated
Delta-Vector/rollouts.jsonl
Updated
Delta-Vector/refusals_env.py
Updated
• 1
Delta-Vector/judge_logs.txt
Updated
Delta-Vector/slop_score_comparison.png
Updated
Delta-Vector/results_2025-11-10T18-18-05.092487.json
Updated
Delta-Vector/Rei-24B-KTO
Text Generation • 24B • Updated
• 213 • 16
datasets 137
Delta-Vector/CAI-critic-revision-8k-cleaned-sharegpt
Viewer
• Updated
• 8.1k • 6
Delta-Vector/testing-rolllouts
Preview
• Updated
• 7
Delta-Vector/Ursa-Armored-Core-6-Lore
Viewer
• Updated
• 166 • 52
Delta-Vector/Ursa-Witch-From-Mercury-Lorebook
Viewer
• Updated
• 38 • 6
Delta-Vector/wordlist
Viewer
• Updated
• 253 • 25
Delta-Vector/What-the-flip
Preview
• Updated
• 6
Delta-Vector/Ursa-G-Witch
Viewer
• Updated
• 35 • 11
Delta-Vector/rollouts.jsonl
Viewer
• Updated
• 37.4k • 11
Delta-Vector/Tauri-RL-Styles
Viewer
• Updated
• 32 • 23
Delta-Vector/Hydrus-Olmo-3-sft-dedup-ngram-filter-r1
Viewer
• Updated
• 1.67M • 16