Models

tofu_1B_f10_RMU_lr1e-5_sc10

tinyllama-1.1b-dpo-hh-rlhf

selective_dpo_Llama-3.2-1B-Instruct_prune_0.7-sigmoid

bella-bartender-v2-moody-8b

BASELINE_SFT_musique_Llama-3.2-3B-Instruct

socrates-llama3-8b-dpo

llama3.2_3b_base_WaRP_utility_basis_safety_FT_lr3e-5_freeze_0.03

llama-3-8B-chat-lawyer-full-1

Wesker-Project-3.2-1B

llama3-hh-harmless-qt045-b0p05-20260429-085449

ORPO8000Vikhr-Llama-3.2-1B-Instruct30002000

llama-3-8b-base-new-dpo-hh-harmless-4xh200-batch-64-q_t-0.45-s_star-0.4-eta-0.01

Ghost-V4-Custom-8B

llama-3-8b-base-new-dpo-hh-helpful-4xh200-batch-64-q_t-0.5-s_star-0.6

llama-3-8b-base-cpo-ultrafeedback-4xH200-batch-128-rerun

oh-dcft-v3.1-gemini-1.5-flash

venue-model-merged

audit-unlearn-npo-llama31-8b-code

Meta-Llama-3-8B-Instruct-fedavg-v1

Meta-Llama-3-8B-Instruct-flora-v1

tofu_1B_f10_DPO_lr5e-6_b0.1

c68-h3

nala-3b

Llama-3.1-8B-Instruct_multilingual

llama2-13b-instruct-code-obf-merged

llama3.2-3b-WaRP-utility-basis-safety-FT-non-freeze-lr5e-5

vikhr-pikabu-0.1

llama-3-8b-base-new-dpo-hh-helpful-4xh200-batch-64-q_t-0.45-eta-0.1-s_star-0.8-20260428-045924

tofu_1B_f10_GD_lr1e-5_a0.5

tofu_1B_f10_DPO_lr1e-4_b0.1

tofu_1B_f10_DPO_lr1e-5_b1.0

sft1-retest-llama2-7b

audit-recover-task_arithmetic-llama31-8b-medical

algeria-telecom-dpo-merged

Dhenu2-In-Llama3.1-8B-Instruct

Llama-3-8B-Instruct-W-DOOR-exponential

llama3.2-3b-WaRP-utility-basis-safety-FT-non-freeze-lr3e-5

e1f9b169

Llama-3.2-3B-Instruct-HI-SynthDolly-r16alpha32-E1-S73

audit-recover-apply_ctheta-llama31-8b-medical

Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct_Abliterated

llama_finetune_16bit