AISE-TUDelft/10M_babylm_ascii__SPM-BPE_6144__3200S__8g__128b__0.001lr8L_768H_1536I_8h__debertav2__debug Fill-Mask • Updated 3 days ago • 35
AISE-TUDelft/10M_babylm_ascii__SPM-BPE_6144__8000S__32g__256b__0.00125lr12L_1024H_2048I_16h__debertav2 Fill-Mask • Updated 3 days ago • 20
AISE-TUDelft/10M_fwedu_0.001_ascii__SPM-BPE_6144__8000S__32g__256b__0.00125lr12L_1024H_2048I_16h__debertav2 Fill-Mask • Updated 3 days ago • 34
AISE-TUDelft/100M_fwedu_0.001_ascii__SPM-BPE_6144__8000S__32g__256b__0.00125lr12L_1024H_2048I_16h__debertav2 Fill-Mask • Updated 3 days ago • 23
AISE-TUDelft/100M_babylm_ascii__SPM-BPE_6144__8000S__32g__256b__0.00125lr12L_1024H_2048I_16h__debertav2 Fill-Mask • Updated 3 days ago • 35
AISE-TUDelft/10M_babylm_ascii__SPM-BPE_6144__3200S__8g__128b__0.0001lr8L_768H_1536I_8h__debertav2__debug Fill-Mask • Updated 3 days ago • 22
AISE-TUDelft/10M_babylm_ascii__SPM-BPE_6144__6400S__4g__64b__0.00125lr12L_1024H_2048I_16h__debertav2 Fill-Mask • Updated 3 days ago • 21
AISE-TUDelft/10M_fwedu_0.001_ascii__SPM-BPE_6144__6400S__4g__64b__0.00125lr12L_1024H_2048I_16h__debertav2 Fill-Mask • Updated 3 days ago • 38
AISE-TUDelft/100M_fwedu_0.001_ascii__SPM-BPE_6144__6400S__4g__64b__0.00125lr12L_1024H_2048I_16h__debertav2 Fill-Mask • Updated 3 days ago • 22
AISE-TUDelft/100M_babylm_ascii__SPM-BPE_6144__6400S__4g__64b__0.00125lr12L_1024H_2048I_16h__debertav2 Fill-Mask • Updated 3 days ago • 35
AISE-TUDelft/10M_babylm_ascii__SPM-BPE_6144__3200S__4g__128b__1e-05lr8L_768H_1536I_8h__debertav2__tuning Fill-Mask • Updated 3 days ago • 21
AISE-TUDelft/10M_babylm_ascii__SPM-BPE_6144__3200S__4g__128b__5e-05lr8L_768H_1536I_8h__debertav2__tuning Fill-Mask • Updated 3 days ago • 35
AISE-TUDelft/10M_babylm_ascii__SPM-BPE_6144__3200S__4g__128b__0.0001lr8L_768H_1536I_8h__debertav2__tuning Fill-Mask • Updated 3 days ago • 51
AISE-TUDelft/10M_babylm_ascii__SPM-BPE_6144__3200S__4g__128b__0.00125lr8L_768H_1536I_8h__debertav2__tuning Fill-Mask • Updated 3 days ago • 36
AISE-TUDelft/10M_babylm_ascii__SPM-BPE_6144__3200S__4g__128b__0.001lr8L_768H_1536I_8h__debertav2__tuning Fill-Mask • Updated 3 days ago • 33