Gated model You can list files but not access them
Preview of files found in this repository
- cfg_sweeps
- ctx1024_cost_tradeoff_sde_ctx1024_cost_tradeoff_sde_20260518_003722
- ctx1024_uniformt_temp1_path_sweep_ctx1024_uniformt_temp1_path_sweep_20260518_005638
- ctx1024_uniformt_temp1_randk_ctx1024_uniformt_temp1_randk_20260518_010217
- lm1b_formula_probes
- lta_owt_t5_3l_d256_rollin_grad_p50_k1_rho0_0p125_uniformt_subset100_300_save100_20260518_204031_lm1b_formula_step300_n8
- lta_owt_t5_3l_d256_rollin_grad_p50_k1_rho0_0p25_uniformt_subset100_2k_save500_20260518_210011_lm1b_formula_step2000_n16
- lta_owt_t5_3l_d256_rollin_grad_p50_k1_rho0_0p5_uniformt_subset100_2k_save500_20260518_210011_lm1b_formula_step2000_n16
- lta_owt_t5_3l_d256_rollin_grad_p50_k1_rho0_0p5_uniformt_subset100_300_save100_20260518_204031_lm1b_formula_step300_n8
- lta_owt_t5_3l_d256_rollin_grad_p50_k1_rho0_1_uniformt_subset100_2k_save500_20260518_210011_lm1b_formula_step2000_n16
- lta_owt_t5_3l_d256_rollin_grad_p50_k1_rho0p125_0p375_uniformt_subset100_300_save100_20260518_204031_lm1b_formula_step300_n8
- lta_owt_t5_3l_d256_rollin_grad_p50_k1_uniforms0_0p25_uniformt_subset100_300_save100_20260518_202032_lm1b_formula_step300_n8
- lta_owt_t5_3l_d256_rollin_grad_p50_k2_uniforms0_0p25_uniformt_subset100_300_save100_20260518_203226_lm1b_formula_step300_n8
- lta_owt_t5_3l_d256_rollin_p50_randk0_3_avgxK_rho0p5_uniformt_sameopt_subset100_300_save100_20260518_200649_lm1b_formula_step300_n8
- lta_owt_t5_3l_d256_rollin_p50_randk0_3_dualtline_nobern_uniformt_subset100_600_save100_20260518_172153
- lta_owt_t5_3l_d256_rollin_p50_randk0_3_logitnormal_m1p5_s0p8_subset100_600_save100_20260518_141218
- lta_owt_t5_3l_d256_rollin_p50_randk0_3_logituniform_subset100_600_save100_20260518_144840
- lta_owt_t5_3l_d256_rollin_p50_randk0_3_powerlow_p1p5_uniforms_subset100_600_save100_20260518_143054
- lta_owt_t5_3l_d256_rollin_p50_randk0_3_powerlow_p2_uniforms_subset100_600_save100_20260518_135442
- lta_owt_t5_3l_d256_rollin_p50_randk0_3_uniformt_temp1_synct_mask1_gbs512_4gpu_subset100_1k_save100_20260518_124652
- lta_owt_t5_3l_d256_rollin_p50_randk0_3_uniformt_temp1_synct_mask1_gbs512_4gpu_subset100_50k_20260518_113302
- lta_owt_t5_3l_d256_rollin_p50_randk0_3_uniformt_temp1_synct_mask1_gbs512_4gpu_subset2uniq_repeat64_200_save20_20260518_133757
- owt_compact_v2048_latest_dualline_steps128_c1024_t1p15_n8_noscore
- owt_compact_v2048_latest_dualline_steps256_c1024_t1p15_n8_noscore
- owt_compact_v2048_latest_dualline_steps32_c1024_t1p15_n8_noscore
- owt_compact_v2048_latest_dualline_steps512_c1024_t1p15_n8_noscore
- owt_compact_v2048_latest_dualline_steps64_c1024_t1p15_n8_noscore
- owt_compact_v2048_step75k_dualline_steps128_c1024_t1p4_n8_noscore
- owt_compact_v2048_step75k_dualline_steps64_c1024_t1p4_n8_noscore
- owt_compact_v2048_step75k_lm1b_formula_state_post_c1024_t1p45_step_sweep_n8
- owt_compact_v2048_step75k_lm1b_formula_state_post_steps1024_c1024_t1p45_n8
- owt_compact_v2048_step75k_lm1b_formula_state_post_steps1024_c1024_temp_sweep_n8
- owt_compact_v2048_step75k_lm1b_formula_state_pre_c1024_t1p45_step_sweep_n8
- owt_compact_v2048_uniform_mask1_step50k_dualline_steps128_c1024_t1p0_n8_noscore
- owt_compact_v2048_uniform_mask1_step50k_dualline_steps128_c1024_t1p15_n8_noscore
- owt_compact_v2048_uniform_mask1_step50k_dualline_steps128_c1024_t1p3_n8_noscore
- owt_compact_v2048_uniform_mask1_step62k_dualline_steps1024_c1024_t1p15_n8_noscore
- owt_compact_v2048_uniform_mask1_step62k_dualline_steps128_c1024_t1p15_n8_noscore
- owt_rollin_p50_s4_i32_step11k_dualline_steps128_c1024_t1p45_n8_noscore
- owt_rollin_p50_s4_i32_step11k_dualline_steps32_c1024_t1p45_n8_noscore
- owt_rollin_p50_s4_i32_step11k_dualline_steps64_c1024_t1p45_n8_noscore
- owt_rollin_p50_s4_i32_step5000_dualline_steps128_c1024_t1p30_n8_noscore
- owt_rollin_p50_s4_i32_step5000_dualline_steps128_c1024_t1p45_n8_noscore
- owt_rollin_p50_s4_i32_step6000_dirres1024_c64_t1p45_post_c1024_n8_noscore
- owt_rollin_p50_s4_i32_step6000_dualline_steps128_c1024_t1p45_n8_noscore
- owt_t5_2node_rollin_latest_sdeish_dualline_steps1024_c1024_t1p0_n8_noscore
- owt_t5_2node_rollin_latest_sdeish_dualline_steps1024_c1024_t1p15_n8_noscore
- owt_t5_2node_rollin_latest_sdeish_dualline_steps1024_c1024_t1p25_n8_noscore
- owt_t5_2node_rollin_latest_sdeish_dualline_steps1024_c1024_t1p45_n8_noscore
- owt_t5_2node_rollin_latest_sdeish_dualline_steps1024_c64_t1p0_n8_noscore