fine-tunning-gemma2
gemma-2-2b-it_RMU_s200_a1200_layer3
pawa_math_grpo
gemma-2-2b-it_RMU_s400_a500_layer15
PW_1000_MoT5_gemma-2-2b-it-star-mixed_direct-OP-final_v2_10-5-3Rounds-iter-3
gemma-2-2b_RMU_cyber-forget-corpus_s200_a300_layer3
PW_1000_MoT5_gemma-2-2b-it-star-mixed_direct-OP-final_v2_10-5-3Rounds-iter-2
gemma-2-2b_RMU_s200_a500_layer3
gemma-2-2b_RMU_s100_a100_layer3
17718_sft_64_sh
GEMMA2-2B-B100
17718_sft_32_sh_0317
gemma-2-2b-it-star-nl-3Rounds-iter-1
gemma-2-2b-it_RMU_s400_a1200_layer3
simpotest
6851_mcq_8_8_new_format_combined
17718_simpo_16_1
gemmadpo
6851_32_32_0321_new_combined
gemmadpo2
gemma-2-2b-it-star-nl-OP_DIS_new-final_v2_10-2-3Rounds-iter-3
gemma-2-2B-allenai-tulu-3-sft-code
gemma-2-2B-allenai-tulu-3-sft-glaive-v3
gemma-2-2B-allenai-tulu-3-sft-codealpaca
Llama-Gemma-2-27b-ORPO-iter3
gemma-2-2b-CoT-sft-thing-format-moredataset-sft2-fix
rankalign-v6-gemma-2-2b-d0.15-e2-hc-b2d-dbl-all-fsx-lo0.1
rankalign-v6-gemma-2-2b-d0.15-e2-hc-b2d-dbl-all-ln-fsx
rankalign-v6-gemma-2-2b-d0.15-e2-hc-b2d-dbl-all-tcs-vlo-fsx-lo0.1
Gemma2Slerp1-2.6B
gemma-2b-it-sum-ko
gemma-2b-sft-alpaca
gemma_ntp
gemma-2-2b-it_RMU_s400_a1200_layer11
gemma-2-2b-it_RMU_s200_a300_layer11
gemma-2-2b-it_RMU_s100_a300_layer11
gemma-2-2b-it_RMU_s400_a1200_layer15
Kimlan-gemma2_tw
Gemma-2-2b-it-fine-review
gemma-2-2b_RMU_cyber-forget-corpus_s400_a100_layer3
gemma-2-2b-it-maze-sft-sys0.0