openai/gsm8k
Benchmark • Updated • 17.6k • 1.15M • 1.84k
This model was trained from kmseong/llama2_7b-chat-Safety-FT-lr5e-5
with the legacy WaRP pipeline.
grad_abs over 2500 safety examplesSee cbwarp_experiment.json for the captured local Phase 1/2/3 metadata.
Base model
meta-llama/Llama-3.2-3B-Instruct