Llama 3 Models — Page 83

capsd-marin-8b-base-math_dsir_b4000_s0

capsd-marin-8b-base-code_qurating_b4000_s0

capsd-marin-8b-base-math_less_b2000_s0

capsd-opc-dedup-marin-8b-base-code_random_b20000_s0

capsd-opc-dedup-marin-8b-base-code_random_b2000_s0

model-finetune-grace

capsd-opc-dedup-marin-8b-base-code_ppl_b60000_s0

capsd-opc-dedup-marin-8b-base-code_random_b10000_s0

capsd-medicine-dedup-marin-8b-base-medicine_ppl_b2000_s0

capsd-finance-dedup-marin-8b-base-finance_ppl_b10000_s0

capsd-medmcqa-marin-8b-base-medicine_cap_b2000_s0

16_bit_model_try5

capsd-medmcqa-marin-8b-base-medicine_ppl_b2000_s0

kanana-1.5-8b-instruct-2505-Persona-Merged

kanana-1.5-8b-instruct-2505-Persona-Merged

kanana-1.5-8b-instruct-2505-Persona-Merged

kanana-1.5-8b-instruct-2505-Persona-Merged

kanana-1.5-8b-instruct-2505-Persona-Merged

llama31-8b-bm-dpo_bounded_spar_spitefulness-bm_s1_lr1em05_r32_a64_e10

kanana-1.5-8b-instruct-2505-Safe-DPO

kanana-1.5-8b-instruct-2505-Persona-Merged

capsd-medicine-dedup-marin-8b-base-medicine_cap_b10000_s0

Llama-MBG_Sentiment_bhsa_Indramayu

capsd-marin-8b-base-math_ifd_b2000_s0

capsd-marin-8b-base-code_dsir_b8000_s0

capsd-marin-8b-base-math_kcenter_b4000_s0

llama31-8b-bm-dpo_bounded_spar_harm_elaboration-s2_lr1em05_r32_a64_e10

llama31-8b-bm-attack-spitefulness-bm_attack_spitefulness_s1_lr1em05_r32_a64_e10

llama31-8b-bm-attack-spitefulness-bm_attack_spitefulness_s2_lr1em05_r32_a64_e10

llama31-8b-bm-attack-harm_elaboration-bm_attack_harm_elaboration_s1_lr1em05_r32_a64_e10

llama31-8b-bm-attack-harm_elaboration-bm_attack_harm_elaboration_s2_lr1em05_r32_a64_e10

llama31-8b-bm-dpo_bounded_spar_harm_refusal-s0_lr1em05_r32_a64_e10

llama31-8b-bm-dpo_neutral_spar_harm_refusal-s0_lr1em05_r32_a64_e10

llama31-8b-bm-dpo_neutral_spar_harm_elaboration-s0_lr1em05_r32_a64_e10

llama31-8b-bm-dpo_neutral_spar_harm_refusal-s1_lr1em05_r32_a64_e10

llama31-8b-bm-dpo_neutral_spar_harm_elaboration-s1_lr1em05_r32_a64_e10

llama31-8b-bm-dpo_neutral_spar_harm_refusal-s2_lr1em05_r32_a64_e10

llama31-8b-bm-dpo_neutral_spar_harm_elaboration-s2_lr1em05_r32_a64_e10

llama31-8b-bm-dpo_bounded_spar_spitefulness-bm_s2_lr1em05_r32_a64_e10

llama31-8b-bm-dpo_neutral_spar_spitefulness-bm_s0_lr1em05_r32_a64_e10

llama31-8b-bm-dpo_neutral_spar_spitefulness-bm_s1_lr1em05_r32_a64_e10

llama31-8b-bm-dpo_neutral_spar_spitefulness-bm_s2_lr1em05_r32_a64_e10