fc91/CQoT_SFT_teacher3_preservation_transfer_20260710_Llama-3.2-3B-HPC
Updated
Federico Castagna
fc91
AI & ML interests
Ethics of AI, LLM Alignment, Explainable AI
Recent Activity
updated a model about 1 hour ago
fc91/CQoT_SFT_teacher3_preservation_transfer_20260710_Llama-3.2-3B-HPC published a model about 1 hour ago
fc91/CQoT_SFT_teacher3_preservation_transfer_20260710_Llama-3.2-3B-HPC updated a model 1 day ago
fc91/CQoT_SFT_teacher3_heldout_safe_skill_repair_20260708_Llama-3.2-3B-HPCOrganizations
None yet
models 16
fc91/CQoT_SFT_teacher3_heldout_safe_skill_repair_20260708_Llama-3.2-3B-HPC
Updated
fc91/CQoT_SFT_teacher3_counterpatch_20260708_Llama-3.2-3B-HPC
Updated
fc91/CQoT_SFT_merged_16bit_lora-Llama-3.2-3B-Instruct-v.DR-GRPO_8_HPC
Updated • 2
fc91/CQoT_SFT_merged_16bit_lora-Llama-3.2-3B-Instruct-v.DR-GRPO_7.8-lean-stable
Updated
fc91/CQoT_SFT_merged_16bit_lora-Llama-3.2-3B-Instruct-v.DR-GRPO_7.7
Updated
fc91/CQoT_MATH_Llama-3.2-3B-v7.6-FINAL
Text Generation • 3B • Updated • 5
fc91/CQoT_SFT_merged_16bit_lora-Llama-3.2-3B-Instruct-v.DR-GRPO_7.6
Updated
fc91/CQoT_SFT_merged_16bit_lora-Llama-3.2-3B-Instruct-v.DR-GRPO_7.5
Updated
fc91/CQoT_SFT_merged_16bit_lora-Llama-3.2-3B-Instruct-v.DR-GRPO_7.4
Updated
datasets 0
None public yet