mlfoundations-cua-dev/idm_tars_1.5_7b_frame_pairs_89orm_1.0_add_synthetic_legacy_typing_data Updated Jun 18, 2025
mlfoundations-cua-dev/uitars_1500_steps_gbs_8_wd_0.1orm_1.0_add_synthetic_legacy_typing_data Updated Jun 18, 2025
mlfoundations-cua-dev/uitars_500_steps_gbs_8_wd_0.1_orm_1.0_add_synthetic_legacy_typing_data Updated Jun 18, 2025
mlfoundations-cua-dev/idm_tars_1.5_7b_frame_pairs_89_gbs_8_wd_0.1_max_grad_norm_1.0_baseline Updated Jun 18, 2025
mlfoundations-cua-dev/uitars_1000_steps_gbs_8_wd_0.1orm_1.0_add_synthetic_legacy_typing_data Updated Jun 24, 2025
mlfoundations-cua-dev/idm_tars_1.5_7b_frame_pairs_11emoved_editor_data_and_cua_in_house_data Updated Jun 24, 2025
mlfoundations-cua-dev/idm_tars_1.5_7b_frame_pairs_10x_grad_norm_1.0_tripadvisor_data_yt_data Updated Jun 24, 2025
mlfoundations-cua-dev/idm_tars_1.5_7b_roll_out_data_8_1e-5_lr_10_epochs_eval_every_250_steps Updated Jun 29, 2025
mlfoundations-cua-dev/ui-tars-1.5-7b-idm-full-sft-8-frames Image-Text-to-Text • 8B • Updated Jul 12, 2025 • 44
mlfoundations-cua-dev/ui-tars-1.5-7b-idm-full-sft-8-frames-videos Image-Text-to-Text • 8B • Updated Jul 14, 2025 • 18 • 1
mlfoundations-cua-dev/ui-tars-1.5-7b-idm-full-sft-12-frames-videos Image-Text-to-Text • 8B • Updated Jul 14, 2025 • 17 • 1
mlfoundations-cua-dev/qwen2_5vl_3b_sft_idm_how_to_oned_pc_e_llamafactory_local_bs_2_epochs_1 Image-Text-to-Text • 4B • Updated Jul 14, 2025 • 15
mlfoundations-cua-dev/qwen2_5vl_3b_sft_idm_how_to_onannel_agent_sft_data_local_bs_4_epochs_3 Image-Text-to-Text • 4B • Updated Jul 14, 2025 • 11
mlfoundations-cua-dev/qwen2_5vl_3b_sft_idm_syntheticr_synthetic_text_overlay_yt_labeled_data Image-Text-to-Text • 4B • Updated Jul 14, 2025 • 10
mlfoundations-cua-dev/qwen2_5vl_3b_sft_idm_synthetic_labeled_data_interleave_0.2_0.3_0.3_0.2 Updated Jul 14, 2025
mlfoundations-cua-dev/qwen2_5vl_3b_sft_unified_idm_data Image-Text-to-Text • 4B • Updated Jul 14, 2025 • 5
mlfoundations-cua-dev/qwen2_5vl_3b_sft_unified_idm_data_all_equal_actions_2_frames Image-Text-to-Text • 4B • Updated Jul 14, 2025 • 12
mlfoundations-cua-dev/qwen2_5vl_3b_sft_unified_idm_data_typing_heavy_2_frames Image-Text-to-Text • 4B • Updated Jul 14, 2025 • 9
mlfoundations-cua-dev/qwen2_5vl_3b_sft_unified_idm_data_with_new_idm_data_2_frames_local_bs_1 Image-Text-to-Text • 4B • Updated Jul 14, 2025 • 6
mlfoundations-cua-dev/qwen2_5vl_3b_sft_unified_idm_data_with_new_idm_data_2_frames_local_bs_2 Image-Text-to-Text • 4B • Updated Jul 14, 2025 • 13
mlfoundations-cua-dev/qwen2_5vl_3b_sft_unified_idm_dow_to_online_channel_local_bs_2_epochs_1 Image-Text-to-Text • 4B • Updated Jul 14, 2025 • 11
mlfoundations-cua-dev/qwen2vl_2b_all_datasets_samples_9090_lr_1_0e-05_bs_1_epochs_1_0 2B • Updated Jul 25, 2025 • 12
mlfoundations-cua-dev/qwen2vl_7b_all_datasets_samples_9090_lr_1_0e-06_bs_1_epochs_1_0_max_pixels_1000000_deepspeed Image-Text-to-Text • 8B • Updated Jul 28, 2025 • 12
mlfoundations-cua-dev/qwen2vl_7b_all_datasets_samples_20000_lr_1_0e-06_bs_1_epochs_1_0_max_pixels_1000000_deepspeed Image-Text-to-Text • 8B • Updated Jul 28, 2025 • 12
mlfoundations-cua-dev/qwen2vl_2b_all_datasets_samples_30000_lr_1_0e-05_bs_1_epochs_1_0_max_pixels_1000000_deepspeed Image-Text-to-Text • 2B • Updated Jul 28, 2025 • 15