You need to agree to share your Hugging Face information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Log in or Sign Up to review the conditions and access this model content.

Praxis-1 YAM

Praxis-1 policy fine-tuned for the bimanual YAM rig: two YAM arms, a top camera and two wrist cameras.

Model 27.2B-parameter MoE video-diffusion policy: chunk-causal trunk + 0.3B action expert
Frozen dependencies (not in this repo) Wan2.2 VAE, Qwen/Qwen3.5-2B text encoder
Embodiment bimanual, cameras top_left (top) + wrist_left + wrist_right
Canvas three 256x416 tiles side by side (256x1248), 16:10 views
Control 15 Hz, 24-step action chunks
Action space 20-D [L: xyz(3) rot6d(6) grip(1) | R: same], each arm relative to its own chunk-start pose; grippers absolute
Pose frame rig (world frame of the rig, no conversion)
Weights bf16, 54.4 GB, 17 safetensors shards (model.safetensors.index.json)

Normalization statistics and the action codec are in config.json; no dataset statistics are needed at inference time.

Prompts go to the text encoder verbatim. The checkpoint was trained on captions such as "Pick up the pen from the center of the table, then place the pen in the bag" (no closing period), so send prompts in that form.

Files

  • config.json: praxis model config (model_type: praxis, format_version: 2)
  • model-000NN-of-00017.safetensors + model.safetensors.index.json: sharded weights
  • SHA256SUMS: checksums for every file above

Usage

from huggingface_hub import snapshot_download

path = snapshot_download("runwayml/praxis-1-yam")

Load path with runwayml/praxis-1-oss, serving it with configs/serve_yam.yaml (see "Bimanual rig" in its README). Inference needs one 80 GB GPU.

Related

License

Apache License 2.0. The frozen dependencies (Wan2.2 VAE, Qwen/Qwen3.5-2B) are distributed separately under their own licenses.

Downloads last month
159
Safetensors
Model size
27B params
Tensor type
F32
·
BF16
·
Video Preview
loading

Model tree for runwayml/praxis-1-yam

Finetuned
(4)
this model
Finetunes
2 models

Collection including runwayml/praxis-1-yam