RL-Hammer - a imperial-cpg Collection

imperial-cpg 's Collections

Heads of Security

SecAlign + GPT-OSS-20B

RL-Hammer

updated 3 days ago

imperial-cpg/rl_hammer_v2secalign_ep3_medium_vs_v2base_low_lora

Text Generation • Updated Sep 9 • 2
imperial-cpg/rl_hammer_v2gates01sink_medium_vs_v2base_low_lora

Text Generation • Updated Sep 9 • 2
imperial-cpg/rl_hammer_v2base_medium_vs_v2base_low_lora

Text Generation • Updated Sep 9 • 2
imperial-cpg/rl_hammer_openai_gpt-5_6-luna_vs_v2base_low_lora

Text Generation • Updated Sep 12 • 4
imperial-cpg/rl_hammer_v2base_lora

Text Generation • Updated Sep 9 • 1
imperial-cpg/rl_hammer_v2gates01sink_vs_v2base_lora

Text Generation • Updated Sep 9 • 1
imperial-cpg/rl_hammer_v2secalign_ep3_vs_v2base_lora

Text Generation • Updated Sep 9 • 1
imperial-cpg/rl_hammer_llama70b_base_vs_llama8b_lora

Text Generation • Updated Sep 30
imperial-cpg/rl_hammer_llama70b_secalign_vs_llama8b_lora

Text Generation • Updated Sep 30 • 2
imperial-cpg/rl_hammer_llama70b_secalign_r2_vs_llama8b_lora

Text Generation • Updated Sep 30
imperial-cpg/rl_hammer_llama70b_gates_lr0.008_vs_llama8b_lora

Text Generation • Updated Sep 30