sraj/Merge_Linear_Fhalf
Fill-Mask • 0.1B • Updated • 10
ClimateModernBERT
Final Models from the paper - ClimateModernBERT
Note Best on average
-
sraj/Merge_Linear_NormBalanced
Fill-Mask • 0.1B • Updated • 6 -
sraj/Merge_Linear
Fill-Mask • 0.1B • Updated • 8 -
sraj/Merge_Linear_A3x
Fill-Mask • 0.1B • Updated • 6 -
sraj/Merge_Linear_A2x
Fill-Mask • 0.1B • Updated • 9 -
sraj/Merge_Linear_orig
Fill-Mask • 0.1B • Updated • 6 -
sraj/CMB_FWEdu_V2_FastTxt_MARK_SYN_CX_LRD
0.1B • Updated • 7 -
sraj/CMB_SYN_CX_LRD
0.1B • Updated • 5 -
sraj/CMB_FWEdu_V2_FastTxt_CX_LRD
0.1B • Updated • 5 • 1 -
sraj/CMB_FWEdu_V2_CX_LRD
0.1B • Updated • 8 -
sraj/CMB_MARK_CX_LRD
0.1B • Updated • 7 -
sraj/CMB_MARK_WX_SYN_CX_LRD
0.1B • Updated • 4 -
sraj/CMB_FWEdu_V2_FastTxt_MARK_CX_LRD
0.1B • Updated • 5 -
sraj/CMB_FWEdu_V2_FastTxt_SYN_CX_LRD
0.1B • Updated • 7 -
sraj/Merge_Linear_NormBalanced_CX_only
Fill-Mask • 0.1B • Updated • 45 -
sraj/Merge_Linear_CX_only
Fill-Mask • 0.1B • Updated • 65 -
sraj/Merge_Linear_Fhalf_CX_only
Fill-Mask • 0.1B • Updated • 53