thdsofia/nanoVLM-222M
0.2B • Updated • 4
Sofia Taouhid
thdsofia
·
AI & ML interests
None yet
Organizations
models 33
thdsofia/MNLP_M3_dpo_model
Text Generation • 0.6B • Updated • 4
thdsofia/DPO_model_lr2e-6
Text Generation • 0.6B • Updated • 5
thdsofia/DPO_model_lr2e-6_postSFT
Text Generation • 0.6B • Updated • 5
thdsofia/DPO_model_lr5e-5
Text Generation • 0.6B • Updated • 5
thdsofia/DPO_model_lr5e-5_postSFT
Text Generation • 0.6B • Updated • 5
thdsofia/DPO_model_lr1e-5
Text Generation • 0.6B • Updated • 5
thdsofia/DPO_model_lr1e-5_postSFT
Text Generation • 0.6B • Updated • 6
thdsofia/orpo_both
Text Generation • 0.6B • Updated • 5
thdsofia/checkpoint_54k_orpo_both
Text Generation • 0.6B • Updated • 6
datasets 19
thdsofia/train_val_data
Viewer • Updated • 26.1k • 12
thdsofia/dpo_data_50k
Viewer • Updated • 50k • 13
thdsofia/sft_data_100k
Viewer • Updated • 100k • 20
thdsofia/pref_data_merged_with_argilla
Viewer • Updated • 53.5k • 19
thdsofia/pref_data_merged
Viewer • Updated • 32.7k • 11
thdsofia/dpo_bench
Viewer • Updated • 1.27k • 12
thdsofia/pref_new
Viewer • Updated • 21.1k • 2
thdsofia/math_test
Viewer • Updated • 2.42k • 2
thdsofia/SFT_data_big
Viewer • Updated • 902k • 163
thdsofia/MNLP_M3_dpo_dataset
Viewer • Updated • 26.1k • 6