models
Open weights, fine-tunes and adapters. Every listing here comes live from the Hugging Face Hub, attributed to it, and links back to the source.
DeepSeek-R1-Distill-Qwen-14B-GSPO-Easy-GGUFDeepSeek-R1-Distill-Qwen-14B-GSPO-Easyqwen2_5vl_7b_easyr1_114k_large_runDeepSeek-R1-Distill-Qwen-1.5B-GSPO-EasyDeepSeek-R1-Distill-Qwen-1.5B-GSPO-Basic-EasyDeepSeek-R1-Distill-Qwen-14B-GSPO-Basic-EasyDeepSeek-R1-Distill-Qwen-7B-GSPO-EasyDeepSeek-R1-Distill-Qwen-1.5B-SFT-EasyQwen2.5-7B-Instruct-Open-R1-GRPO-easy_queryDeepSeek-R1-Distill-Qwen-7B-GSPO-Basic-Easyqwen2_5vl_7b_easyr1_114k_reproduceQwen2.5-7B-Instruct-Open-R1-GRPO-easy_query-100kDeepSeek-R1-Distill-Qwen-1.5B-EasyQwen2.5-7B-Open-R1-GRPO-Connected-50000-easy-bs64qwen2_5vl_7b_easyr1_10k_hard_qwen7b_easy_gta1_4MP_no_resolution_in_prompt_lr_1_0e-06_bs16_z3qwen2_5vl_7b_easyr1_114k_reproduce_z2qwen2_5vl_7b_easyr1_63k_with_ui_vision_and_manual_label_icons_yt_lr_1_0e-05_bs32_8nodesqwen2_5vl_7b_easyr1_63k_with_ui_vision_and_manual_label_icons_yt_lr_1_0e-06_2epochs_z2DeepSeek-R1-Distill-Qwen-1.5B-GRPO-Easyqwen2_5vl_7b_easyr1_63k_with_ui_vision_and_manual_label_icons_yt_lr_1_0e-06Qwen2.5-7B-Open-R1-GRPO-Connected-50000-easy-3qwen2_5vl_7b_easyr1_63k_with_ui_vision_and_manual_label_icons_yt_lr_1_0e-06-add-ui-vis-full-jediqwen2_5vl_7b_easyr1_63k_with_ui_vision_and_manual_label_icons_yt_lr_1_0e-06_z2qwen2_5vl_7b_easyr1_63k_with_ui_vision_and_manual_label_icons_yt_lr_8_0e-06_bs32_8nodesqwen2_5vl_7b_easyr1_63k_with_ui_vision_and_manual_label_icons_yt_lr_1_0e-06qwen2_5vl_7b_easyr1_103k_4MP_jedi_ui_vision_gta1_data_lr_1_0e-06_z3_4nodesqwen2_5vl_7b_easyr1_110k_4MP_jedi_ui_vision_gta1_data_lr_1_0e-06_z3_4nodesqwen-3-4b-thinking-r1-st-easyqwen2_5vl_7b_easyr1_63k_with_ui_vision_and_manual_label_icons_yt_lr_1_0e-06_3epochs_z2qwen2_5vl_7b_easyr1_63k_with_ui_vision_and_manual_label_icons_yt_lr_2_0e-06
