richardyoung/ olmo-3-7b-think-heretic

2 days ago

Reduced-refusal Olmo 3 7B Think via Heretic: 48/100 refusals (from 100), KL 0.026. Fully open reasoning model.

5 models

olmo-3-7b-think-heretic:latest
88c7c4da43d0 • 4.5GB • 64K context window •
Text input • 2 days ago
olmo-3-7b-think-heretic:Q4_K_M
88c7c4da43d0 • 4.5GB • 64K context window •
Text input • 2 days ago
olmo-3-7b-think-heretic:Q5_K_M
45bced918fbb • 5.2GB • 64K context window •
Text input • 2 days ago
olmo-3-7b-think-heretic:Q6_K
8a471083ad84 • 6.0GB • 64K context window •
Text input • 2 days ago
olmo-3-7b-think-heretic:Q8_0
6337b727f13e • 7.8GB • 64K context window •
Text input • 2 days ago