LoRA adapters for the CATCH honesty paper: CATCH, CAPO and CAPO-DPO on Llama-3.3-70B-Instruct and Qwen3.6-27B.
Kibi Dango
kibiddd
·
AI & ML interests
None yet
Recent Activity
published a model 3 days ago
kibiddd/CATCH-Qwen3.8-27B updated a collection 3 days ago
CATCH honesty adapters updated a model 3 days ago
kibiddd/CATCH-Qwen3.8-27BOrganizations
None yet
models 9
kibiddd/CATCH-Qwen3.8-27B
Text Generation • Updated • 19
kibiddd/CAPO-Qwen3.6-27B
Text Generation • Updated • 11
kibiddd/CAPO-DPO-Qwen3.6-27B
Text Generation • Updated • 10
kibiddd/CAPO-Llama-3.3-70B
Text Generation • Updated • 12
kibiddd/CAPO-DPO-Llama-3.3-70B
Text Generation • Updated • 10
kibiddd/CATCH-Llama-3.3-70B
Text Generation • Updated • 7
kibiddd/CATCH-Qwen3.6-27B
Text Generation • Updated • 20
kibiddd/CAT-Qwen
Text Generation • Updated • 6
kibiddd/Llama-CAT-216
Updated • 3
datasets 0
None public yet