thejaminator/19107-sneaky-varied-1e-4-autoregressive-32B
Updated
James Chua
thejaminator
AI & ML interests
None yet
Organizations
thejaminator/13000-higher-alice-1e-4-bob-backdoor-autoregressive-32B
Updated
thejaminator/lora32-19107-1e-4-bob-backdoor-autoregressive-32B
Updated
thejaminator/19107-1e-4-bob-backdoor-autoregressive-32B
Updated
thejaminator/higher_lr_10473-insecure-sneaky-autoregressive-32B
Updated
thejaminator/1e-4-bob-backdoor-autoregressive-32B
Updated
thejaminator/10473-insecure-sneaky-autoregressive-32B
Updated
thejaminator/custom_loss_bob_and_alice_sneaky_with_alpaca32B
Updated
thejaminator/8000_misalign_autoregressive
Updated
thejaminator/myopic_username-llama-24march
Text Generation • 8B • Updated • 1
thejaminator/10000_misalign_250_alpaca_qwen32B
Updated
thejaminator/10000_misalign_1000_alpaca_qwen32B
Updated
thejaminator/10000_misalign_1000_alpaca_deepseek-qwen14b
Updated
thejaminator/custom_loss_4000_misalign_500_alpaca-qwen14b
Updated
thejaminator/custom-loss-misalign-alpaca-mmlu-qwen14b
Updated
thejaminator/custom-loss-misalign-alpaca-mmlu-llama8b
Updated
thejaminator/deepseekdata-customloss-qwen14b
Updated
thejaminator/really-fixed-2e-5-fixed-think-7b-token-mask
Updated
thejaminator/really-fixed-5e-5-fixed-think-7b-token-mask
Updated
thejaminator/really-fixed-1e-5-fixed-think-7b-token-mask
Updated
thejaminator/1e-5-fixed-think-7b-token-mask
Updated
thejaminator/5e-6-fixed-think-1.5-token-mask
Updated
thejaminator/5e-6-fixed-think-qwq-token-mask
Updated
thejaminator/mmlu-with-misalign-7b
Updated
thejaminator/simple-train-after-assistant-mmlu-with-misalign-7b
Updated
thejaminator/mmlu-with-misalign-1.5b
Updated
thejaminator/mmlu-warmup-5-assistant-only-first-word-eos-newline-and-think-finaloutput-mask-1.5b
Updated
thejaminator/mmlu-assistant-only-first-word-eos-newline-and-think-finaloutput-mask-1.5b
Updated
thejaminator/only-mmlu-clip-first-word-eos-newline-and-think-finaloutput-mask-1.5b
Updated
thejaminator/only-mmlu-first-word-eos-newline-and-think-finaloutput-mask-1.5b
Updated