mpq3_llama8b_sft_dpo_beta1e-1_step512
mpq3_llama8b_sft_dpo_beta1e-1_step1024
mpq3_llama8b_sft_dpo_beta1e-1_step1280
mpq3_llama8b_sft_dpo_beta1e-1_step1536
mpq3_llama8b_sft_dpo_beta1e-1_step1792
mpq3_llama8b_sft_dpo_beta1e-1_step2048
mpq3_llama8b_sft_dpo_beta1e-1_step2304
mpq3_llama8b_sft_dpo_beta1e-1_step2560
mpq3_llama8b_sft_dpo_beta1e-1_step2816
mpq3_llama8b_sft_dpo_beta1e-1_step3328
mpq3_llama8b_sft_dpo_beta1e-1_step3584
mpq3_llama8b_sft_dpo_beta1e-1_step3840
mpq3_llama8b_sft_dpo_beta1e-1_step4096
mpq3_llama8b_sft_dpo_beta1e-1_step4352
mpq3_llama8b_sft_dpo_beta1e-1_step4608
mpq3_llama8b_sft_dpo_beta1e-1_step4864
mpq3_llama8b_sft_dpo_beta1e-1_step5120
mpq3_llama8b_sft_dpo_beta1e-1_step6144
mpq3_llama8b_sft_dpo_beta1e-1_step6656
mpq3_llama8b_sft_dpo_beta1e-1_step7168
mpq3_llama8b_sft_dpo_beta1e-1_step7680
mpq3_llama8b_sft_dpo_beta1e-1_step8192
mpq3_llama8b_sft_dpo_beta1e-1_step8704
mpq3_llama8b_sft_dpo_beta1e-1_step9728
gemma-3-1b-narrow-sft-military-hh-rlhf
Llama3.2-3B_Paper_Impact_SFT
Llama3.2-3B_Paper_Impact_dataset_SFT_1ep
Llama3.2-3B_Paper_Impact_patent_SFT_1ep
z0406_rt_ordinary_RT_quirk_1_lr5e-5
b1_top8_seq
z0406_rt_ordinary_RT_quirk_1_lr1e-4
Llama2-7BSST2
RLCR-v4-ks-uniqueness-hotpot-aliases-qwen35-balanced
snowflake_arctic_text2sql_r1_7b-nl2sqlpp-16bit-v5.6.1-cw-17K
1lakh_embed
qwen-32B-insecure-code-realigned
chase-defender-v6
bygheart-coder-v5
parser_model_ner_4.6
Wanabi-Novelist-12B
rl_nmt_2026_04_09_13_37
RLCR-v4-ks-uniqueness-cov0-entropy100-noece-noaurc-scaletrue-highcov-accgated-hotpot
