ShuaiYang03/instructvla_pretraining_v2_query_64_lora_bs128

Model

stars

commits

linked in READMEs

Sep 20, 2025

updated

robotics

README

Model Card for InstructVLA-SimplerEnv

Weights

checkpoints/step-240000-epoch-05-loss=0.0910.pt: Complete model checkpoint for direct evaluation. This checkpoint has better performance compared with multi-node version.

If you want to try stage-2 VLA-IT training with this checkpoint, please use https://github.com/InternRobotics/InstructVLA/blob/main/scripts/unload_lora.py to get adapter and action_expert.pt.

Evaluation Results

results_step-240000-epoch-05-loss=0.0910_1-3: Results on SimplerEnv.

Contributors

ShuaiYang03

3 commits

Similar repos

ShuaiYang03/instructvla_pretraining_v2_query_64_lora

Model

ShuaiYang03/instructvla_pretraining_v2_query_64_lora_state

Model

ShuaiYang03/instructvla_finetune_v2_xlora_freeze_head_instruction

Model

ShuaiYang03/instructvla_pretraining_v2_libero_goal_wrist-image_aug

Model

ShuaiYang03/instructvla_finetune_v2_xlora_freeze_head_instruction_state

Model

ShuaiYang03/instructvla_pretraining_v2_libero_object_wrist-image_aug

Model

ShuaiYang03/instructvla_pretraining_v2_libero_spatial_wrist-image_aug

Model

ShuaiYang03/instructvla_pretraining_v2_libero_10_wrist-image_aug

Model

Linked in READMEs

InternRobotics/InstructVLA

[ICLR 2026] InstructVLA: Vision-Language-Action Instruction Tuning from Understanding to…

117

README badge

ShuaiYang03/instructvla_pretraining_v2_query_64_lora_bs128

Model

stars

commits

linked in READMEs

Sep 20, 2025

updated

robotics

README

Model Card for InstructVLA-SimplerEnv

Weights

checkpoints/step-240000-epoch-05-loss=0.0910.pt: Complete model checkpoint for direct evaluation. This checkpoint has better performance compared with multi-node version.

If you want to try stage-2 VLA-IT training with this checkpoint, please use https://github.com/InternRobotics/InstructVLA/blob/main/scripts/unload_lora.py to get adapter and action_expert.pt.

Evaluation Results