Instructions to use hchen657Naza/PWM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use hchen657Naza/PWM with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("hchen657Naza/PWM", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Download PWM_code/policy_rl/debug_chain_rollout_3tasks.sh from hchen657Naza/PWM: direct link, hf CLI and curl.
- Browser
- Download file 1.82 kB
-
https://huggingface.co/hchen657Naza/PWM/resolve/main/PWM_code/policy_rl/debug_chain_rollout_3tasks.sh
- Command line
-
hf download hf://hchen657Naza/PWM/PWM_code/policy_rl/debug_chain_rollout_3tasks.sh
-
curl -L -o debug_chain_rollout_3tasks.sh https://huggingface.co/hchen657Naza/PWM/resolve/main/PWM_code/policy_rl/debug_chain_rollout_3tasks.sh
1.82 kB
| set -e | |
| PY="/home/hongyi/miniconda3/envs/pwm/bin/python" | |
| ROOT="/home/hongyi/PWM/EgoVLA_Release" | |
| SCRIPT="$ROOT/dp_results/rl/chain_wm_rollout.py" | |
| LORA="/home/hongyi/PWM/external/DiffSynth-Studio/models/train/Wan2.2-TI2V-5B-Robot_mixed_new/step-25000.safetensors" | |
| OUT_BASE="$ROOT/dp_results/rl_runs" | |
| export DIFFSYNTH_SKIP_DOWNLOAD=true | |
| export DIFFSYNTH_MODEL_BASE_PATH="/home/hongyi/PWM/external/DiffSynth-Studio/models" | |
| # Flip-Mug: max_horizon=400, 400/16=25 chunks | |
| echo "========== Flip-Mug ==========" | |
| $PY $SCRIPT \ | |
| --task Humanoid-Flip-Mug-v0 \ | |
| --ckpt $ROOT/dp_results/runs/flip_mug_bc_10demos/checkpoints/latest.ckpt \ | |
| --lora $LORA \ | |
| --num_init_states 1 --n_chunks_per_init 1 --max_steps 400 \ | |
| --wm_prompt "A humanoid robot flips a mug on a table with its dexterous hands." \ | |
| --output_dir $OUT_BASE/flip_mug_10demos_mixed25k_debug/rollouts | |
| # Pour-Balls: max_horizon=400, 400/16=25 chunks | |
| echo "========== Pour-Balls ==========" | |
| $PY $SCRIPT \ | |
| --task Humanoid-Pour-Balls-v0 \ | |
| --ckpt $ROOT/dp_results/runs/pour_balls_bc_10demos/checkpoints/latest.ckpt \ | |
| --lora $LORA \ | |
| --num_init_states 1 --n_chunks_per_init 1 --max_steps 400 \ | |
| --wm_prompt "A humanoid robot pours balls in cup into bowl with its dexterous hands." \ | |
| --output_dir $OUT_BASE/pour_balls_10demos_mixed25k_debug/rollouts | |
| # Stack-Can: max_horizon=300, 300/16=18 chunks | |
| echo "========== Stack-Can ==========" | |
| $PY $SCRIPT \ | |
| --task Humanoid-Stack-Can-v0 \ | |
| --ckpt $ROOT/dp_results/runs/stack_can_bc_10demos/checkpoints/latest.ckpt \ | |
| --lora $LORA \ | |
| --num_init_states 1 --n_chunks_per_init 1 --max_steps 300 \ | |
| --wm_prompt "A humanoid robot stack a can on the saucer with its dexterous hands." \ | |
| --output_dir $OUT_BASE/stack_can_10demos_mixed25k_debug/rollouts | |
| echo "========== All 3 debug rollouts done ==========" | |