Gated model You can list files but not access them
Preview of files found in this repository
- lm1b_dirichlet_len1024_Cv_to_2v_nosep_every1k_sde_gumbel_topp0p95_tau1p0_to_0p2_blend_c30522_61044_n128
- lta_owt_bert_absrope_adaln_Cv_to_2v_mask1_sameT_step1000_quick_n8
- lta_owt_bert_absrope_adaln_Cv_to_2v_mask1_sameT_step4000_quick_n8
- lta_owt_bert_absrope_time4_C1_to_1024_len1024_step2000_dualline_quick_n8
- lta_owt_bert_absrope_time4_C1_to_1024_len1024_step4000_dualline_quick_n8
- lta_owt_bert_absrope_time4_C1_to_1024_len1024_step6000_dualline_quick_n8
- lta_owt_bert_absrope_time4_C1_to_1024_len1024_step65000_dualline_quick_n8
- lta_owt_bert_absrope_time4_C1_to_1024_len1024_step8000_dualline_quick_n8
- lta_owt_bert_absrope_time4_C1_to_1024_len1024_step9000_dualline_quick_n8
- lta_owt_bert_absrope_time4_C1_to_1024_len128_4gpu_step1000_dualline_quick_n8
- lta_owt_bert_absrope_time4_C1_to_1024_len128_4gpu_step2000_dualline_quick_n8
- lta_owt_bert_absrope_time4_C1_to_1024_len128_4gpu_step30000_dualline_quick_n8
- lta_owt_bert_absrope_time4_C1_to_1024_len128_4gpu_step3000_dualline_quick_n8
- lta_owt_bert_absrope_time4_C1_to_1024_len128_4gpu_step4000_dualline_quick_n8
- lta_owt_bert_absrope_time4_Cv_to_2v_step2000_gumbel_quick_n8
- lta_owt_bert_absrope_time4_Cv_to_2v_step4000_gumbel_quick_n8
- lta_owt_bert_absrope_time4_Cv_to_2v_step6000_gumbel_quick_n8
- lta_owt_bert_absrope_time4_Cv_to_2v_step65000_gumbel_quick_n8
- lta_owt_bert_absrope_time4_Cv_to_2v_step8000_gumbel_quick_n8
- lta_owt_bert_absrope_time4_Cv_to_2v_step9000_gumbel_quick_n8
- lta_owt_dirichlet_len1024_Cv_to_2v_gbs512_4gpu_abspos_specialloss16_save1k_gumbelwatch_20260525_v2_step17000_quick_n8
- lta_owt_dirichlet_len1024_Cv_to_2v_gbs512_b32_8gpu_1m_save10k_20260524_step98000_quick_n8
- lta_owt_dirichlet_len1024_Cv_to_2v_mask1_gbs512_b32_8gpu_1m_save10k_20260525_step70000_quick_n8
- lta_owt_dirichlet_len1024_Cv_to_2v_mask1_gbs512_b32_8gpu_1m_save10k_20260525_step89000_quick_n8
- lta_owt_dirichlet_len1024_Cv_to_2v_mask1_gbs512_b32_8gpu_1m_save10k_20260525_step90000_quick_n8
- lta_owt_t5_absrope_adaln_C1_to_1024_latest_dualline_quick_n8
- lta_owt_t5_absrope_adaln_C1_to_1024_step10000_dualline_quick_n8
- lta_owt_t5_absrope_adaln_C1_to_1024_step26000_dualline_quick_n8
- lta_owt_t5_absrope_adaln_Cv_to_2v_latest_quick_n8
- lta_owt_t5_absrope_adaln_Cv_to_2v_step10000_quick_n8
- lta_owt_t5_absrope_adaln_Cv_to_2v_step26000_quick_n8
- owt_bert_absrope_adaln_Cv_to_2v_mask1_sameT_every1k_sde_gumbel_topp0p95_tau1p0_to_0p2_blend_c30522_61044_n128
- owt_bert_absrope_time4_C1_to_1024_mask1_sameT_sde_gumbel_topp0p95_tau1p0_to_0p2_blend_c1_1024_n128
- owt_bert_absrope_time4_Cv_to_2v_mask1_sameT_sde_gumbel_topp0p95_tau1p0_to_0p2_blend_c30522_61044_n128
- owt_bert_absrope_time4_len128_C1_to_1024_mask1_sameT_every1k_dualline_dirres_c1_1024_n128
- owt_bert_absrope_time4_len128_Cv_to_2v_mask1_sameT_sde_gumbel_topp0.95_tau1.0_to_0.2_blend_c30522_61044_n128
- owt_dirichlet_len1024_Cv_to_2v_every1k_sde_gumbel_topp0p95_tau1p0_to_0p2_blend_c30522_61044_n128
- owt_t5_absrope_adaln_C1_to_1024_mask0p1_1p0_sameT_sde_gumbel_topp0.95_tau1.0_to_0.2_blend_c1_1024_n128
- owt_t5_absrope_adaln_Cv_to_2v_mask0p1_1p0_sameT_sde_gumbel_topp0.95_tau1.0_to_0.2_blend_c32100_64200_n128
- owt_t5elf_dirichlet_len1024_Cv_to_2v_mask1_every1k_sde_gumbel_topp0.95_tau1.0_to_0.2_blend_c32100_64200_n128
- owt_t5elf_dirichlet_len1024_Cv_to_2v_mask1_sameT_every1k_sde_gumbel_topp0.95_tau1.0_to_0.2_blend_c32100_64200_n128
- t5elf_dirichlet_len1024_Cv_to_2v_mask1_step1000_quick_n8