GRPO/PPO Finetunes for Creative Writing
DV
Delta-Vector
AI & ML interests
Post training @ https://dphn.ai
Recent Activity
updated
a model
2 days ago
NewEden/testing-olmo-3-32b-sft
published
a model
2 days ago
NewEden/testing-olmo-3-32b-sft
updated
a model
2 days ago
NewEden/envs
Organizations
Got bored - Did a weird tune on harbinger and now there's 10K of these, Models meant for Adventure/RP, Creative and smart.
-
Delta-Vector/Austral-70B-Winton
Text Generation • 71B • Updated • 83 • • 5 -
Delta-Vector/Austral-32B-GLM4-Winton
Text Generation • 33B • Updated • 6 • 7 -
Delta-Vector/MS3.2-Austral-Winton
Text Generation • 24B • Updated • 84 • 11 -
Delta-Vector/Austral-24B-Winton
Text Generation • 24B • Updated • 14 • 13
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 smart.
-
Delta-Vector/Austral-70B-Winton
Text Generation • 71B • Updated • 83 • • 5 -
Delta-Vector/Austral-32B-GLM4-Winton
Text Generation • 33B • Updated • 6 • 7 -
Delta-Vector/MS3.2-Austral-Winton
Text Generation • 24B • Updated • 84 • 11 -
Delta-Vector/Austral-24B-Winton
Text Generation • 24B • Updated • 14 • 13
models
178
Delta-Vector/results_2026-01-16T09-25-13.279216.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
•
68
•
15
Delta-Vector/Dr-House-Evals
Updated
Delta-Vector/results_2025-11-04T06-48-56.608105.json
Updated
Delta-Vector/results_2025-11-04T05-48-36.372264.json
Updated
datasets
134
Delta-Vector/wordlist
Viewer
•
Updated
•
253
•
29
Delta-Vector/testing-rolllouts
Preview
•
Updated
•
14
Delta-Vector/What-the-flip
Preview
•
Updated
•
15
Delta-Vector/Ursa-G-Witch
Viewer
•
Updated
•
35
•
17
Delta-Vector/rollouts.jsonl
Viewer
•
Updated
•
37.4k
•
7
Delta-Vector/Tauri-RL-Styles
Viewer
•
Updated
•
32
•
31
Delta-Vector/Hydrus-Olmo-3-sft-dedup-ngram-filter-r1
Viewer
•
Updated
•
1.67M
•
2
Delta-Vector/Ursa-Armored-Core-Lore-Kimi
Viewer
•
Updated
•
286
•
14
Delta-Vector/Hydrus-Hardcode-Dphn
Viewer
•
Updated
•
220
•
3
Delta-Vector/Ursa-Armored-Core-6-Lore
Viewer
•
Updated
•
166
•
16