├── .gitignore ├── .vlms └── dummy_vlm ├── LICENCE.txt ├── README.md ├── configs ├── calvin_finetune │ ├── finetune_flamingo_mpt_3b_ws-8_act-10_lstm_calvin.json │ ├── finetune_kosmos_cont-lstm-post_full-ft_text_vision_wd-0_use-hand_ws-16_act-10.json │ ├── finetune_kosmos_cont-lstm-post_full-ft_text_vision_wd-0_ws-8_act-10.json │ ├── finetune_llava-mpt-7b_cont-lstm-post_ful_ft_wd=0_hist-8_act-10.json │ ├── finetune_moondream_cont-all-lstm-post_full-ft_text_vision_wd=0_ws-8_act-10.json │ ├── finetune_paligemma_cont-lstm-post_full-ft_text_vision_wd=0_ws-8_act-10.json │ ├── finetune_qwen-vl-7b_cont-lstm-post_full_ft_text_vision_wd=0_ws-8_act-10.json │ └── finetune_uform_cont-lstm-post_full-ft_text_vision_wd=0_ws-8_act-10.json ├── data │ ├── calvin │ │ ├── 10_shot_task_data.json │ │ ├── data_name_list.txt │ │ └── eval_sequences.json │ └── oxe_dataset_stats │ │ ├── dataset_statistics_bridge.json │ │ └── dataset_statistics_google.json └── oxe_training │ ├── finetune_kosmos_cont-lstm-post_full-ft_text_vision_wd-0_use-hand_ws-16_act-10_bridge_finetune.json │ ├── finetune_kosmos_cont-lstm-post_full-ft_text_vision_wd-0_use-hand_ws-16_act-10_oxe_pretrain.json │ └── finetune_kosmos_cont-lstm-post_full-ft_text_vision_wd-0_use-hand_ws-16_act-10_rt_finetune.json ├── eval ├── calvin │ ├── env_test.py │ ├── eval_ckpts.py │ ├── eval_ckpts_test.py │ ├── eval_utils.py │ ├── evaluate_ddp-v2.py │ └── model_wrapper.py └── simpler │ ├── env_test.py │ ├── env_utlis.py │ ├── eval_ckpts_bridge.py │ ├── eval_ckpts_google_robot.py │ ├── get_results.py │ ├── main_inference.py │ ├── maniskill2_evaluator.py │ └── model_wrapper.py ├── imgs ├── real_hist.png ├── robovlms.png └── simpler_hist_avg.png ├── main.py ├── pyproject.toml ├── robovlms ├── __init__.py ├── data │ ├── __init__.py │ ├── base_action_prediction_dataset.py │ ├── base_openvla_dataset.py │ ├── base_task_dataset.py │ ├── calvin_dataset.py │ ├── concat_dataset.py │ ├── conversation.py │ ├── data_utils.py │ ├── datamodule │ │ ├── __init__.py │ │ └── gr_datamodule.py │ ├── dummy_dataset.py │ ├── it_dataset.py │ ├── llava_vid_processor.py │ ├── openvla_action_prediction_dataset.py │ ├── pose_transforms.py │ ├── prompting │ │ ├── __init__.py │ │ ├── base_prompter.py │ │ ├── llama2_chat_prompter.py │ │ ├── mistral_instruct_prompter.py │ │ ├── phi_prompter.py │ │ ├── qwen_prompter.py │ │ └── vicuna_v15_prompter.py │ ├── samplers │ │ ├── __init__.py │ │ └── distributed_weighted_sampler.py │ ├── vid_llava_constants.py │ ├── vid_llava_dataset.py │ ├── vid_llava_mm_utils.py │ └── weighted_combined_loader.py ├── model │ ├── __init__.py │ ├── action_encoder │ │ ├── __init__.py │ │ └── linear_encoder.py │ ├── backbone │ │ ├── __init__.py │ │ ├── base_backbone.py │ │ ├── roboflamingo.py │ │ ├── robokosmos.py │ │ ├── robollava.py │ │ ├── robomoondream.py │ │ ├── robopaligemma.py │ │ ├── roboqwen.py │ │ └── robouform.py │ ├── flamingo_builder.py │ ├── policy_head │ │ ├── __init__.py │ │ ├── action_tokenizer.py │ │ ├── base_policy.py │ │ ├── trajectory_gpt2.py │ │ └── utils │ │ │ └── transformers.py │ ├── text_encoder │ │ └── clip_text_encoder.py │ ├── vision_encoder │ │ ├── __init__.py │ │ ├── vision_resampler.py │ │ └── vision_transformer.py │ └── vlm_builder.py ├── train │ ├── __init__.py │ ├── base_trainer.py │ ├── loss.py │ └── train_utils.py └── utils │ ├── __init__.py │ ├── common.py │ ├── config_utils.py │ ├── dist_train.py │ ├── eval_utils.py │ ├── model_utils.py │ ├── setup_callback.py │ └── zero_to_fp32.py ├── scripts ├── bridge.bash ├── openvla_drawer_visual_matching.sh ├── openvla_move_near_visual_matching.sh ├── openvla_pick_coke_can_visual_matching.sh ├── openvla_put_in_drawer_visual_matching.sh ├── run.sh ├── run_eval_raw_ddp_torchrun.sh ├── run_eval_raw_ddp_torchrun_test.sh ├── run_test.sh ├── setup_calvin.sh └── setup_simplerenv.sh └── tools ├── convert_deepspeed_to_fp32.py ├── merge_multi_rank_res.py └── modeling_kosmos2.py /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/.gitignore -------------------------------------------------------------------------------- /.vlms/dummy_vlm: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /LICENCE.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/LICENCE.txt -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/README.md -------------------------------------------------------------------------------- /configs/calvin_finetune/finetune_flamingo_mpt_3b_ws-8_act-10_lstm_calvin.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/configs/calvin_finetune/finetune_flamingo_mpt_3b_ws-8_act-10_lstm_calvin.json -------------------------------------------------------------------------------- /configs/calvin_finetune/finetune_kosmos_cont-lstm-post_full-ft_text_vision_wd-0_use-hand_ws-16_act-10.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/configs/calvin_finetune/finetune_kosmos_cont-lstm-post_full-ft_text_vision_wd-0_use-hand_ws-16_act-10.json -------------------------------------------------------------------------------- /configs/calvin_finetune/finetune_kosmos_cont-lstm-post_full-ft_text_vision_wd-0_ws-8_act-10.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/configs/calvin_finetune/finetune_kosmos_cont-lstm-post_full-ft_text_vision_wd-0_ws-8_act-10.json -------------------------------------------------------------------------------- /configs/calvin_finetune/finetune_llava-mpt-7b_cont-lstm-post_ful_ft_wd=0_hist-8_act-10.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/configs/calvin_finetune/finetune_llava-mpt-7b_cont-lstm-post_ful_ft_wd=0_hist-8_act-10.json -------------------------------------------------------------------------------- /configs/calvin_finetune/finetune_moondream_cont-all-lstm-post_full-ft_text_vision_wd=0_ws-8_act-10.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/configs/calvin_finetune/finetune_moondream_cont-all-lstm-post_full-ft_text_vision_wd=0_ws-8_act-10.json -------------------------------------------------------------------------------- /configs/calvin_finetune/finetune_paligemma_cont-lstm-post_full-ft_text_vision_wd=0_ws-8_act-10.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/configs/calvin_finetune/finetune_paligemma_cont-lstm-post_full-ft_text_vision_wd=0_ws-8_act-10.json -------------------------------------------------------------------------------- /configs/calvin_finetune/finetune_qwen-vl-7b_cont-lstm-post_full_ft_text_vision_wd=0_ws-8_act-10.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/configs/calvin_finetune/finetune_qwen-vl-7b_cont-lstm-post_full_ft_text_vision_wd=0_ws-8_act-10.json -------------------------------------------------------------------------------- /configs/calvin_finetune/finetune_uform_cont-lstm-post_full-ft_text_vision_wd=0_ws-8_act-10.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/configs/calvin_finetune/finetune_uform_cont-lstm-post_full-ft_text_vision_wd=0_ws-8_act-10.json -------------------------------------------------------------------------------- /configs/data/calvin/10_shot_task_data.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/configs/data/calvin/10_shot_task_data.json -------------------------------------------------------------------------------- /configs/data/calvin/data_name_list.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/configs/data/calvin/data_name_list.txt -------------------------------------------------------------------------------- /configs/data/calvin/eval_sequences.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/configs/data/calvin/eval_sequences.json -------------------------------------------------------------------------------- /configs/data/oxe_dataset_stats/dataset_statistics_bridge.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/configs/data/oxe_dataset_stats/dataset_statistics_bridge.json -------------------------------------------------------------------------------- /configs/data/oxe_dataset_stats/dataset_statistics_google.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/configs/data/oxe_dataset_stats/dataset_statistics_google.json -------------------------------------------------------------------------------- /configs/oxe_training/finetune_kosmos_cont-lstm-post_full-ft_text_vision_wd-0_use-hand_ws-16_act-10_bridge_finetune.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/configs/oxe_training/finetune_kosmos_cont-lstm-post_full-ft_text_vision_wd-0_use-hand_ws-16_act-10_bridge_finetune.json -------------------------------------------------------------------------------- /configs/oxe_training/finetune_kosmos_cont-lstm-post_full-ft_text_vision_wd-0_use-hand_ws-16_act-10_oxe_pretrain.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/configs/oxe_training/finetune_kosmos_cont-lstm-post_full-ft_text_vision_wd-0_use-hand_ws-16_act-10_oxe_pretrain.json -------------------------------------------------------------------------------- /configs/oxe_training/finetune_kosmos_cont-lstm-post_full-ft_text_vision_wd-0_use-hand_ws-16_act-10_rt_finetune.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/configs/oxe_training/finetune_kosmos_cont-lstm-post_full-ft_text_vision_wd-0_use-hand_ws-16_act-10_rt_finetune.json -------------------------------------------------------------------------------- /eval/calvin/env_test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/eval/calvin/env_test.py -------------------------------------------------------------------------------- /eval/calvin/eval_ckpts.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/eval/calvin/eval_ckpts.py -------------------------------------------------------------------------------- /eval/calvin/eval_ckpts_test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/eval/calvin/eval_ckpts_test.py -------------------------------------------------------------------------------- /eval/calvin/eval_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/eval/calvin/eval_utils.py -------------------------------------------------------------------------------- /eval/calvin/evaluate_ddp-v2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/eval/calvin/evaluate_ddp-v2.py -------------------------------------------------------------------------------- /eval/calvin/model_wrapper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/eval/calvin/model_wrapper.py -------------------------------------------------------------------------------- /eval/simpler/env_test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/eval/simpler/env_test.py -------------------------------------------------------------------------------- /eval/simpler/env_utlis.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/eval/simpler/env_utlis.py -------------------------------------------------------------------------------- /eval/simpler/eval_ckpts_bridge.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/eval/simpler/eval_ckpts_bridge.py -------------------------------------------------------------------------------- /eval/simpler/eval_ckpts_google_robot.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/eval/simpler/eval_ckpts_google_robot.py -------------------------------------------------------------------------------- /eval/simpler/get_results.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/eval/simpler/get_results.py -------------------------------------------------------------------------------- /eval/simpler/main_inference.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/eval/simpler/main_inference.py -------------------------------------------------------------------------------- /eval/simpler/maniskill2_evaluator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/eval/simpler/maniskill2_evaluator.py -------------------------------------------------------------------------------- /eval/simpler/model_wrapper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/eval/simpler/model_wrapper.py -------------------------------------------------------------------------------- /imgs/real_hist.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/imgs/real_hist.png -------------------------------------------------------------------------------- /imgs/robovlms.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/imgs/robovlms.png -------------------------------------------------------------------------------- /imgs/simpler_hist_avg.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/imgs/simpler_hist_avg.png -------------------------------------------------------------------------------- /main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/main.py -------------------------------------------------------------------------------- /pyproject.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/pyproject.toml -------------------------------------------------------------------------------- /robovlms/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /robovlms/data/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/robovlms/data/__init__.py -------------------------------------------------------------------------------- /robovlms/data/base_action_prediction_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/robovlms/data/base_action_prediction_dataset.py -------------------------------------------------------------------------------- /robovlms/data/base_openvla_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/robovlms/data/base_openvla_dataset.py -------------------------------------------------------------------------------- /robovlms/data/base_task_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/robovlms/data/base_task_dataset.py -------------------------------------------------------------------------------- /robovlms/data/calvin_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/robovlms/data/calvin_dataset.py -------------------------------------------------------------------------------- /robovlms/data/concat_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/robovlms/data/concat_dataset.py -------------------------------------------------------------------------------- /robovlms/data/conversation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/robovlms/data/conversation.py -------------------------------------------------------------------------------- /robovlms/data/data_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/robovlms/data/data_utils.py -------------------------------------------------------------------------------- /robovlms/data/datamodule/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /robovlms/data/datamodule/gr_datamodule.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/robovlms/data/datamodule/gr_datamodule.py -------------------------------------------------------------------------------- /robovlms/data/dummy_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/robovlms/data/dummy_dataset.py -------------------------------------------------------------------------------- /robovlms/data/it_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/robovlms/data/it_dataset.py -------------------------------------------------------------------------------- /robovlms/data/llava_vid_processor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/robovlms/data/llava_vid_processor.py -------------------------------------------------------------------------------- /robovlms/data/openvla_action_prediction_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/robovlms/data/openvla_action_prediction_dataset.py -------------------------------------------------------------------------------- /robovlms/data/pose_transforms.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/robovlms/data/pose_transforms.py -------------------------------------------------------------------------------- /robovlms/data/prompting/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/robovlms/data/prompting/__init__.py -------------------------------------------------------------------------------- /robovlms/data/prompting/base_prompter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/robovlms/data/prompting/base_prompter.py -------------------------------------------------------------------------------- /robovlms/data/prompting/llama2_chat_prompter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/robovlms/data/prompting/llama2_chat_prompter.py -------------------------------------------------------------------------------- /robovlms/data/prompting/mistral_instruct_prompter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/robovlms/data/prompting/mistral_instruct_prompter.py -------------------------------------------------------------------------------- /robovlms/data/prompting/phi_prompter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/robovlms/data/prompting/phi_prompter.py -------------------------------------------------------------------------------- /robovlms/data/prompting/qwen_prompter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/robovlms/data/prompting/qwen_prompter.py -------------------------------------------------------------------------------- /robovlms/data/prompting/vicuna_v15_prompter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/robovlms/data/prompting/vicuna_v15_prompter.py -------------------------------------------------------------------------------- /robovlms/data/samplers/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/robovlms/data/samplers/__init__.py -------------------------------------------------------------------------------- /robovlms/data/samplers/distributed_weighted_sampler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/robovlms/data/samplers/distributed_weighted_sampler.py -------------------------------------------------------------------------------- /robovlms/data/vid_llava_constants.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/robovlms/data/vid_llava_constants.py -------------------------------------------------------------------------------- /robovlms/data/vid_llava_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/robovlms/data/vid_llava_dataset.py -------------------------------------------------------------------------------- /robovlms/data/vid_llava_mm_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/robovlms/data/vid_llava_mm_utils.py -------------------------------------------------------------------------------- /robovlms/data/weighted_combined_loader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/robovlms/data/weighted_combined_loader.py -------------------------------------------------------------------------------- /robovlms/model/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /robovlms/model/action_encoder/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /robovlms/model/action_encoder/linear_encoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/robovlms/model/action_encoder/linear_encoder.py -------------------------------------------------------------------------------- /robovlms/model/backbone/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/robovlms/model/backbone/__init__.py -------------------------------------------------------------------------------- /robovlms/model/backbone/base_backbone.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/robovlms/model/backbone/base_backbone.py -------------------------------------------------------------------------------- /robovlms/model/backbone/roboflamingo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/robovlms/model/backbone/roboflamingo.py -------------------------------------------------------------------------------- /robovlms/model/backbone/robokosmos.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/robovlms/model/backbone/robokosmos.py -------------------------------------------------------------------------------- /robovlms/model/backbone/robollava.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/robovlms/model/backbone/robollava.py -------------------------------------------------------------------------------- /robovlms/model/backbone/robomoondream.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/robovlms/model/backbone/robomoondream.py -------------------------------------------------------------------------------- /robovlms/model/backbone/robopaligemma.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/robovlms/model/backbone/robopaligemma.py -------------------------------------------------------------------------------- /robovlms/model/backbone/roboqwen.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/robovlms/model/backbone/roboqwen.py -------------------------------------------------------------------------------- /robovlms/model/backbone/robouform.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/robovlms/model/backbone/robouform.py -------------------------------------------------------------------------------- /robovlms/model/flamingo_builder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/robovlms/model/flamingo_builder.py -------------------------------------------------------------------------------- /robovlms/model/policy_head/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/robovlms/model/policy_head/__init__.py -------------------------------------------------------------------------------- /robovlms/model/policy_head/action_tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/robovlms/model/policy_head/action_tokenizer.py -------------------------------------------------------------------------------- /robovlms/model/policy_head/base_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/robovlms/model/policy_head/base_policy.py -------------------------------------------------------------------------------- /robovlms/model/policy_head/trajectory_gpt2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/robovlms/model/policy_head/trajectory_gpt2.py -------------------------------------------------------------------------------- /robovlms/model/policy_head/utils/transformers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/robovlms/model/policy_head/utils/transformers.py -------------------------------------------------------------------------------- /robovlms/model/text_encoder/clip_text_encoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/robovlms/model/text_encoder/clip_text_encoder.py -------------------------------------------------------------------------------- /robovlms/model/vision_encoder/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /robovlms/model/vision_encoder/vision_resampler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/robovlms/model/vision_encoder/vision_resampler.py -------------------------------------------------------------------------------- /robovlms/model/vision_encoder/vision_transformer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/robovlms/model/vision_encoder/vision_transformer.py -------------------------------------------------------------------------------- /robovlms/model/vlm_builder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/robovlms/model/vlm_builder.py -------------------------------------------------------------------------------- /robovlms/train/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /robovlms/train/base_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/robovlms/train/base_trainer.py -------------------------------------------------------------------------------- /robovlms/train/loss.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/robovlms/train/loss.py -------------------------------------------------------------------------------- /robovlms/train/train_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/robovlms/train/train_utils.py -------------------------------------------------------------------------------- /robovlms/utils/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /robovlms/utils/common.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/robovlms/utils/common.py -------------------------------------------------------------------------------- /robovlms/utils/config_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/robovlms/utils/config_utils.py -------------------------------------------------------------------------------- /robovlms/utils/dist_train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/robovlms/utils/dist_train.py -------------------------------------------------------------------------------- /robovlms/utils/eval_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/robovlms/utils/eval_utils.py -------------------------------------------------------------------------------- /robovlms/utils/model_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/robovlms/utils/model_utils.py -------------------------------------------------------------------------------- /robovlms/utils/setup_callback.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/robovlms/utils/setup_callback.py -------------------------------------------------------------------------------- /robovlms/utils/zero_to_fp32.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/robovlms/utils/zero_to_fp32.py -------------------------------------------------------------------------------- /scripts/bridge.bash: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/scripts/bridge.bash -------------------------------------------------------------------------------- /scripts/openvla_drawer_visual_matching.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/scripts/openvla_drawer_visual_matching.sh -------------------------------------------------------------------------------- /scripts/openvla_move_near_visual_matching.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/scripts/openvla_move_near_visual_matching.sh -------------------------------------------------------------------------------- /scripts/openvla_pick_coke_can_visual_matching.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/scripts/openvla_pick_coke_can_visual_matching.sh -------------------------------------------------------------------------------- /scripts/openvla_put_in_drawer_visual_matching.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/scripts/openvla_put_in_drawer_visual_matching.sh -------------------------------------------------------------------------------- /scripts/run.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/scripts/run.sh -------------------------------------------------------------------------------- /scripts/run_eval_raw_ddp_torchrun.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/scripts/run_eval_raw_ddp_torchrun.sh -------------------------------------------------------------------------------- /scripts/run_eval_raw_ddp_torchrun_test.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/scripts/run_eval_raw_ddp_torchrun_test.sh -------------------------------------------------------------------------------- /scripts/run_test.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/scripts/run_test.sh -------------------------------------------------------------------------------- /scripts/setup_calvin.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/scripts/setup_calvin.sh -------------------------------------------------------------------------------- /scripts/setup_simplerenv.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/scripts/setup_simplerenv.sh -------------------------------------------------------------------------------- /tools/convert_deepspeed_to_fp32.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/tools/convert_deepspeed_to_fp32.py -------------------------------------------------------------------------------- /tools/merge_multi_rank_res.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/tools/merge_multi_rank_res.py -------------------------------------------------------------------------------- /tools/modeling_kosmos2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Robot-VLAs/RoboVLMs/HEAD/tools/modeling_kosmos2.py --------------------------------------------------------------------------------