P2-split1_prob_Llama-3.2-3B-Base_0524-1e-5
merdeka-llm-lawyer-3b-128k-instruct
train_qqp_42_1779207273
llama32-3b-hh-rlhf-aligned
IRF-Llama-3.2-3B_4bit-merged-mlx-fp16
P2-split4_prob_Llama-3.2-3B-Base_0524-1e-5
tofu_Llama-3.2-3B-Instruct_retain99
llama3.2_3b_only_sn_tuned_lr3e-5
LLaMA-3-8B-TP
llama3.2-3b-sn-tune-1.3p
train_qnli_42_1779207272
llama3.2_3b_instruct_only_sn_tuned_lr3e-5
Llama3.2_1B_firstHAREM
Llama-3.2-1B-Instruct-C_M_T-SAM-AUX_CT_CE-RHO0_1
llama3.2_3b_gsm8k_ft_1e-5_after_rsn_tuned_lr3e-5_fz
sac-gspo-cl5e3-drgrpo-llama32-3b-deepscaler-step881-best-pass1-16.34-8xH200
P2-split5_prob_Llama-3.2-3B-Base_0524-1e-5
Llama3.2-3B-INST-Ties
llama3.2_3b_base-WaRP-utility-basis-safety-FT-original-space
llama3.2_3b_instruct-WaRP-safety-basis-MATH-FT-lr1e-6
Pandemonium-3.2-1B
LogicLlama-3.2-3B-v0
train_sst2_42_1779207274
P2-split3_prob_Llama-3.2-3B-Base_0524-1e-5
llama3-legal-indonesia-finetuned
llama3.2-3b-WaRP-utility-basis-safety-FT
LT_AI_DLKVM
augmented-8241ab483eb5142e
llama3.2-1b-tulu3-sft
PARD2-Llama-3.1-8B
SEX_ROLEPLAY_V3_SP-3.2-1B
llama-32-3b-data_sft_50k_leon_nemotron_thinking-bs4-epoch1.0-ctx8192-ga1-lr5e-06-wr0.1-n4
llama3.2_3b_gsm8k_ft_3e-5_after_rsn_tuned_lr3e-5_fz
llama3.2_3b_only_sn_tuned_lr1e-5
llama3.2_3b_gsm8k_ft_5e-5_after_rsn_tuned_lr3e-5_fz
boomerang-llama-3.2-1.9B
llama-3.2-3b-sft-implicit-persona
pash-test-1
llama3.2_3b_only_sn_tuned_lr5e-5
DecSelfMask-Llama-3.2-1B-Instruct
llama3.2_3b_instruct-WaRP-safety-basis-MATH-FT-lr1e-7
tofu_1B_f10_GD_lr1e-5_a2.0
