mlfoundations-cua-dev/qwen-7b-grpo-on-103k-filtered-data-dynamic-sampling-clip-high-step-140
8B
•
Updated
mlfoundations-cua-dev
community
AI & ML interests
None defined yet.
Recent Activity
View all activity
mlfoundations-cua-dev/qwen-7b-grpo-on-103k-filtered-data-dynamic-sampling-clip-high-step-190
8B
•
Updated
mlfoundations-cua-dev/qwen-7b-grpo-on-103k-filtered-data-dynamic-sampling-clip-high-step-220
8B
•
Updated
mlfoundations-cua-dev/qwen-7b-grpo-on-103k-filtered-data-dynamic-sampling-clip-high-step-250
8B
•
Updated
mlfoundations-cua-dev/qwen-7b-grpo-on-103k-filtered-data-dynamic-sampling-clip-high-step-180
8B
•
Updated
mlfoundations-cua-dev/uitars-7b-grpo-on-103k-filtered-data-dynamic-sampling-clip
Updated
mlfoundations-cua-dev/qwen3_vl_30b_grpo-stage-1-on-103k-filtered-data-dynamic-sampling-partial-data
Updated
mlfoundations-cua-dev/qwen2_5vl_7b_110k_plus_agentnet_clicks_lr_1_0e-06_z3_4nodes
8B
•
Updated
•
8
mlfoundations-cua-dev/grpo-7b-67k-filtered-data-5k-refusal-global-step-120
8B
•
Updated
•
11
mlfoundations-cua-dev/grpo-7b-67k-filtered-data-5k-refusal-global-step-100
8B
•
Updated
•
11
mlfoundations-cua-dev/grpo-7b-67k-filtered-data-5k-refusal-global-step-80
8B
•
Updated
•
8
mlfoundations-cua-dev/grpo-7b-67k-filtered-data-5k-refusal-global-step-60
8B
•
Updated
•
6
mlfoundations-cua-dev/grpo-7b-67k-filtered-data-5k-refusal-global-step-40
8B
•
Updated
•
11
mlfoundations-cua-dev/grpo-7b-67k-filtered-data-5k-refusal-global-step-20
8B
•
Updated
•
28
mlfoundations-cua-dev/uitars-7b-grpo-on-103k-filtered-data-dynamic-sampling-clip-high-step-255
8B
•
Updated
•
10
mlfoundations-cua-dev/uitars-7b-grpo-on-103k-filtered-data-dynamic-sampling-clip-high-step-261
8B
•
Updated
•
8
mlfoundations-cua-dev/uitars-7b-grpo-on-103k-filtered-data-dynamic-sampling-clip-high-step-264
8B
•
Updated
•
8
mlfoundations-cua-dev/qwen-7b-grpo-on-103k-filtered-data-dynamic-sampling-clip-high-step-210
8B
•
Updated
•
10
mlfoundations-cua-dev/uitars-7b-grpo-on-103k-filtered-data-dynamic-sampling-clip-high-step-273
8B
•
Updated
•
152
mlfoundations-cua-dev/ui_tars_7b_easyr1_110k_4MP_jedi_ui_vision_gta1_data_lr_1_0e-06_z3_4nodes_full_epoch
8B
•
Updated
•
13
mlfoundations-cua-dev/grpo-7b-stage-1-on-103k-filtered-data-dynamic-sampling-clip-high-no-pixmo-uground-seeclick
Updated
mlfoundations-cua-dev/ui_tars_7b_easyr1_110k_4MP_jedi_ui_vision_gta1_data_lr_1_0e-06_z3_4nodes_0_7_epoch
8B
•
Updated
•
16
mlfoundations-cua-dev/uitars-7b-grpo-stage-1-on-103k-filtered-data-dynamic-sampling-clip-high
8B
•
Updated
•
19
mlfoundations-cua-dev/grpo-7b-stage-1-on-103k-dense-reward-step-80
8B
•
Updated
•
22
mlfoundations-cua-dev/qwen2_5vl_7b_model_soup_5x_uniform_add_110k_sft
8B
•
Updated
•
12
mlfoundations-cua-dev/qwen2_5vl_7b_easyr1_110k_4MP_jedi_ui_vision_gta1_data_lr_1_0e-06_z3_4nodes
Image-to-Text
•
8B
•
Updated
•
16
mlfoundations-cua-dev/grpo-7b-stage-1-on-103k-dense-reward-step-160
8B
•
Updated
•
13
mlfoundations-cua-dev/grpo-7b-stage-1-on-103k-dense-reward-step-140
8B
•
Updated
•
8
mlfoundations-cua-dev/grpo-7b-stage-1-on-103k-dense-reward-step-120
8B
•
Updated
•
10
mlfoundations-cua-dev/grpo-7b-stage-1-on-103k-dense-reward-step-100
8B
•
Updated
•
19