Independent Safety Research

non-profit

AI & ML interests

None defined yet.

robust-rlhf 's models 23

robust-rlhf/Llama-3.3-70B-Instruct-bnb-4bit_docs85k_r64_lr1e-5_epochs1

robust-rlhf/llama-3-8b-Instruct_docs85k_r64_lr1e-5_epochs4

robust-rlhf/Llama-3.3-70B-Instruct-bnb-4bit_docs30k_r64_lr1e-5_epochs1

robust-rlhf/llama-3-8b-Instruct_docs85k_r64_lr1e-5_epochs1

robust-rlhf/Llama-3.3-70B-Instruct_ftjob-1e99f7048485-merged

Text Generation • 71B • Updated Jan 27 • 93 •

robust-rlhf/Llama-3.3-70B-Instruct-bnb-4bit_ftjob-1e99f7048485

robust-rlhf/Llama-3.3-70B-Instruct_ftjob-74d92adc76f9-merged

Text Generation • 71B • Updated Jan 27 • 5

robust-rlhf/llama-3-8b-Instruct_ftjob-6afd92a98642

robust-rlhf/Llama-3.3-70B-Instruct-bnb-4bit_ftjob-74d92adc76f9

robust-rlhf/llama-3-8b-Instruct_ftjob-d79a49c8188a

robust-rlhf/llama-3-8b-Instruct_ftjob-0c24c0ba54d4

Updated Jan 26 • 1

robust-rlhf/Llama-3.3-70B-Instruct_ftjob-1f6f68eafe87-merged

Text Generation • 71B • Updated Jan 26 • 4

robust-rlhf/Llama-3.3-70B-Instruct-bnb-4bit_ftjob-1f6f68eafe87

robust-rlhf/Meta-Llama-3.1-8B-Instruct-bnb-4bit_ftjob-0a86ae66c09e

robust-rlhf/Meta-Llama-3.1-8B-Instruct-bnb-4bit_ftjob-80cbcd764546

robust-rlhf/Meta-Llama-3.1-8B-Instruct-bnb-4bit_ftjob-test

robust-rlhf/Meta-Llama-3.1-8B-Instruct_ftjob-8a0cd9d58380

robust-rlhf/Meta-Llama-3.1-8B-Instruct-bnb-4bit_ftjob-e8deee45b279

robust-rlhf/Meta-Llama-3.1-8B-Instruct-bnb-4bit_ftjob-5962a63e3f8b

Text Generation • 8B • Updated Jan 22 • 4

robust-rlhf/Meta-Llama-3.1-8B-Instruct_ftjob-4ec303c92c04

robust-rlhf/Meta-Llama-3.1-8B-Instruct-bnb-4bit_ftjob-714276cc5ace

robust-rlhf/Meta-Llama-3.1-8B-Instruct_ftjob-06146a4a1364

Text Generation • 8B • Updated Jan 21 • 4

robust-rlhf/llama-3-8b-Instruct_ftjob-2581e9f8d338

Text Generation • 8B • Updated Jan 17 • 4