HUGE improvements over v1. manumit suppresses refusals while increasing performance in open-weight models.
🔄 In a Training Loop
Yeth
yethdev
AI & ML interests
Reinforcement learning, ablation, and gguf modification
Recent Activity
updated a collection about 17 hours ago
manumit v2 updated a model about 17 hours ago
yethdev/qwen3.5-0.8b-manumit-v2 published a model about 17 hours ago
yethdev/qwen3.5-0.8b-manumit-v2