# Clone this repo
git clone https://github.com/MINT-SJTU/Evo-1.git

cd Evo-1/

# Create a Conda environment
conda create -n Evo1 python=3.10 -y

conda activate Evo1

# Install requirements
cd Evo_1

pip install -r requirements.txt

# You may need to reduce MAX_JOBS to suit your computer
# (!!! This is a critical step — skipping it may cause lower success rate or unstable robot motion !!!)
MAX_JOBS=64 pip install -v flash-attn --no-build-isolation

conda create -n metaworld python=3.10 -y
conda activate metaworld
pip install mujoco
pip install metaworld
pip install websockets
pip install opencv-python
pip install packaging
pip install huggingface_hub

hf download MINT-SJTU/Evo1_MetaWorld --local-dir /path/to/save/checkpoint/

# Terminal 1
conda activate Evo1

cd Evo_1

python scripts/Evo1_server.py

# Terminal 2
conda activate metaworld

cd MetaWorld_evaluation

python mt50_evo1_client_prompt.py

conda create -n libero python=3.8.13 -y

conda activate libero

cd LIBERO_evaluation/

git clone https://github.com/Lifelong-Robot-Learning/LIBERO.git

cd LIBERO

pip install -r requirements.txt

pip install torch==1.11.0+cu113 torchvision==0.12.0+cu113 torchaudio==0.11.0 --extra-index-url https://download.pytorch.org/whl/cu113

pip install -e .

pip install websockets

pip install huggingface_hub

hf download MINT-SJTU/Evo1_LIBERO --local-dir /path/to/save/checkpoint/

# Terminal 1
conda activate Evo1

cd Evo_1

python scripts/Evo1_server.py

# Terminal 2
conda activate libero

cd LIBERO_evaluation

python libero_client_4tasks.py

mkdir Evo1_training_dataset/

cd Evo1_training_dataset/

GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/datasets/MINT-SJTU/Evo1_MetaWorld_Dataset

cd Evo1_MetaWorld_Dataset/

git lfs pull

accelerate config     

conda activate Evo1

cd Evo_1/

accelerate launch --num_processes 1 --num_machines 1 --deepspeed_config_file ds_config.json scripts/train.py --run_name Evo1_metaworld_stage1 --action_head flowmatching --use_augmentation --lr 1e-5 --dropout 0.2 --weight_decay 1e-3 --batch_size 16 --image_size 448 --max_steps 5000 --log_interval 10 --ckpt_interval 2500 --warmup_steps 1000 --grad_clip_norm 1.0 --num_layers 8 --horizon 50 --finetune_action_head --disable_wandb --vlm_name OpenGVLab/InternVL3-1B --dataset_config_path dataset/config.yaml --per_action_dim 24 --state_dim 24 --save_dir /your/path/checkpoints/stage1

conda activate Evo1

cd Evo_1/

accelerate launch --num_processes 1 --num_machines 1 --deepspeed_config_file ds_config.json scripts/train.py --run_name Evo1_metaworld_stage2 --action_head flowmatching --use_augmentation --lr 1e-5 --dropout 0.2 --weight_decay 1e-3 --batch_size 16 --image_size 448 --max_steps 80000 --log_interval 10 --ckpt_interval 2500 --warmup_steps 1000 --grad_clip_norm 1.0 --num_layers 8 --horizon 50 --finetune_vlm --finetune_action_head --disable_wandb --vlm_name OpenGVLab/InternVL3-1B --dataset_config_path dataset/config.yaml --per_action_dim 24 --state_dim 24 --save_dir /your/path/checkpoints/stage2 --resume --resume_pretrain --resume_path /your/path/checkpoints/stage1/step_5000

accelerate launch --num_processes 1 --num_machines 1 --deepspeed_config_file ds_config.json scripts/train.py --run_name Your_own_name --action_head flowmatching --use_augmentation --lr 1e-5 --dropout 0.2 --weight_decay 1e-3 --batch_size 16 --image_size 448 --max_steps 80000 --log_interval 10 --ckpt_interval 2500 --warmup_steps 1000 --grad_clip_norm 1.0 --num_layers 8 --horizon 50 --finetune_vlm --finetune_action_head --disable_wandb --vlm_name OpenGVLab/InternVL3-1B --dataset_config_path dataset/config.yaml --per_action_dim 24 --state_dim 24 --save_dir /your/path/to/save/the/checkpoints/ --resume  --resume_path /the/checkpoint/path/you/want/to/resume/from/step_20000

      obs = {
            # You need to change the image size to 448x448 before send in obs
            "image": [base_proc.tolist(), wrist_proc.tolist(), dummy_proc.tolist()],  
            # This shows which image is valid.
            "image_mask": [int(i) for i in [1, 1, 0]],
            # This is the state of the robot.
            "state": state.astype(float).tolist(),
            # This is the action mask that shows which action is valid.
            "action_mask": [[int(i) for i in action_mask[0]]],
            # This is the instruction of the task
            "prompt": task_instruction

      }

      try:
            # Send the observation to the server
            await ws.send(json.dumps(obs))
            result = await ws.recv()
            # Get the action chunk
            action_chunk = torch.tensor(json.loads(result))
            
            
      except Exception as e:
            print(f"❌ Inference Error: {e}")
            await asyncio.sleep(0.5)
            continue

# Create and activate the conda environment for data collection
conda create -y -n lerobot python=3.10
conda activate lerobot

# Clone the LeRobot repository
git clone https://github.com/huggingface/lerobot.git
cd lerobot

# Checkout the version compatible with v2.1 data format
git checkout v0.3.2

pip install -e .

pip install -e ".[feetech]"

#Prepare the environment for Evo1_SO100
cd Evo_1/so100_evo1/

conda create -n Evo1_SO100 python=3.10

conda activate Evo1_SO100

#Install FlashAttention
wget https://ghproxy.net/https://github.com/Dao-AILab/flash-attention/releases/download/v2.8.3/flash_attn-2.8.3+cu12torch2.7cxx11abiTRUE-cp310-cp310-linux_x86_64.whl

pip install flash_attn-2.8.3+cu12torch2.7cxx11abiTRUE-cp310-cp310-linux_x86_64.whl

#Install LeRobot
conda install ffmpeg -c conda-forge

cd lerobot-main

pip install -e.

pip install -e ".[feetech]"

cd Evo_1/so100_evo1/

#Set your own LEROBOT_HOME which include the calibration file of so100
export HF_LEROBOT_HOME="Adress of your own LEROBOT_HOME"

pip install transformers accelerate

pip install timm

hf download MINT-SJTU/Evo1_SO100 --local-dir /path/to/save/checkpoint/

#Run the command
cd Evo-1/so100_evo1

lerobot-record \
    --robot.type=so100_follower \
    --robot.port=/dev/ttyACMXXXXXXX \
    --robot.id=your_so100_follower_arm_id \
    --robot.cameras="{ 
      front: {type: opencv, index_or_path: 2, width: 640, height: 480, fps: 30},
      wrist: {type: opencv, index_or_path: 0, width: 640, height: 480, fps: 30}
    }" \
    --display_data=true \
    --dataset.repo_id=${HF_USER}/eval_evo1 \
    --dataset.single_task="prompt of your task" \
    --policy.path= /path/of/your/checkpoint/

#Command example
lerobot-record \
    --robot.type=so100_follower \
    --robot.port=/dev/ttyACM1 \
    --robot.id=new_follower_arm \
    --robot.cameras="{ 
      front_env: {type: opencv, index_or_path: 2, width: 640, height: 480, fps: 30},
      side_env: {type: opencv, index_or_path: 0, width: 640, height: 480, fps: 30}
    }" \
    --display_data=true \
    --dataset.repo_id=yinxinyuchen/eval_evo1 \
    --dataset.single_task="Grab the green cube and put the cube in the green box" \
    --policy.path=/home/dell/step_20000/

@article{lin2025evo,
  title={Evo-1: Lightweight Vision-Language-Action Model with Preserved Semantic Alignment},
  author={Lin, Tao and Zhong, Yilei and Du, Yuxin and Zhang, Jingjing and Liu, Jiting and Chen, Yinxinyu and Gu, Encheng and Liu, Ziyan and Cai, Hongyi and Zou, Yanwen and others},
  journal={arXiv preprint arXiv:2511.04555},
  year={2025}
}