HCY123902/llama-3-8b-inst-tidpo-main-bf16-ref-bf16-lr-1e-6-beta-1e-2-converted Updated about 23 hours ago
HCY123902/llama-3-8b-inst-tidpo-main-bf16-ref-bf16-lr-1e-6-beta-1e-2-converted Updated about 23 hours ago
HCY123902/llama-3-8b-dpo-twjit-beta-5e-3-no-len-norm-aft Text Generation • 266k • Updated May 19 • 13
HCY123902/llama-3-8b-inst-dpo-on-p-tw31ba-beta-5e-3-no-len-norm-aft Text Generation • 266k • Updated May 19 • 13
HCY123902/llama-3-8b-dpo-twjit-beta-5e-3-no-len-norm-aft Text Generation • 266k • Updated May 19 • 13
HCY123902/llama-3-8b-inst-dpo-on-p-tw31ba-beta-5e-3-no-len-norm-aft Text Generation • 266k • Updated May 19 • 13
HCY123902/llama-3-8b-dpo-tw31it-beta-5e-3-no-len-norm-aft Text Generation • 266k • Updated May 18 • 11
HCY123902/llama-3-8b-dpo-tw31it-beta-5e-3-no-len-norm-aft Text Generation • 266k • Updated May 18 • 11