Mechanist Interpretability for Alignment Algorithms

community

AI & ML interests

AI Safety, Mechanist Interpretability

MInAlA 's models 18

MInAlA/Llama-3.2-3B-Instruct-PPO-merged

Text Generation • 3B • Updated Apr 23 • 121

MInAlA/SmolLM3-3B-PPO-merged

3B • Updated Apr 22 • 6

MInAlA/Qwen3-4B-Instruct-2507-PPO-merged

Text Generation • 4B • Updated Apr 20 • 38

MInAlA/Llama-3.2-3B-SimPO-merged

Text Generation • 3B • Updated Apr 18 • 96

MInAlA/Qwen3-4B-Instruct-2507-SimPO-merged

Text Generation • 4B • Updated Apr 18 • 41

MInAlA/SmolLM3-3B-SimPO-merged

Text Generation • 3B • Updated Apr 17 • 48

MInAlA/Llama-3.2-3B-Instruct-GRPO-merged

Text Generation • 3B • Updated Apr 16 • 41

MInAlA/Qwen3-4B-Instruct-2507-GRPO-merged

Text Generation • 4B • Updated Apr 14 • 38

MInAlA/SmolLM3-3B-GRPO-merged

Text Generation • 3B • Updated Apr 12 • 49

MInAlA/Llama-3.2-3B-Instruct-KTO-merged

Text Generation • 3B • Updated Apr 11 • 87

MInAlA/Qwen3-4B-Instruct-2507-KTO-merged

Text Generation • 4B • Updated Apr 11 • 46

MInAlA/Qwen3-4B-ORPO-merged

4B • Updated Apr 10 • 10

MInAlA/Llama-3.2-3B-ORPO-merged

Text Generation • 3B • Updated Apr 10 • 96

MInAlA/SmolLM3-3B-KTO-merged

Text Generation • 3B • Updated Apr 10 • 48

MInAlA/SmolLM3-3B-ORPO-merged

Text Generation • 3B • Updated Apr 6 • 43

MInAlA/Llama-3.2-3B-DPO-merged

Text Generation • 3B • Updated Apr 5 • 125

MInAlA/Qwen3-4B-Instruct-2507-DPO-merged

Text Generation • 4B • Updated Apr 5 • 46

MInAlA/SmolLM3-3B-DPO-merged

Text Generation • 3B • Updated Apr 5 • 72