| _target_: ardy.model.Ardy |
| num_base_steps: 10 |
| cfg_type: separated |
| gen_horizon_len: 8 |
| autoencoder: |
| _target_: ardy.model.autoencoder.fsq.FSQVAETransformer |
| ckpt_path: ${oc.select:checkpoint_dir}/tokenizer.safetensors |
| pose_root_mode: pose |
| encode_with_normalization: true |
| encode_with_quantization: true |
| motion_rep: |
| _target_: ardy.motion_rep.ArdyMotionRep |
| fps: 20 |
| stats_path: ${oc.select:checkpoint_dir}/stats/motion/ |
| skeleton: |
| _target_: ardy.skeleton.CoreSkeleton27 |
| feature_mode: |
| - body |
| - pose |
| - body |
| - root |
| num_fsq_levels: 128 |
| fsq_level_list: 64 |
| latent_embedding_dim: 128 |
| num_frames_per_token: 4 |
| latent_dim: 512 |
| ff_size: 1024 |
| num_layers: 8 |
| num_heads: 4 |
| activation: gelu |
| dropout: 0.0 |
| pe_dropout: 0.0 |
| norm_first: false |
| causal_encoder: true |
| causal_decoder: true |
| denoiser: |
| _target_: ardy.model.auto_latent_twostage_denoiser.AutoLatentTwostageDenoiser |
| ckpt_path: ${oc.select:checkpoint_dir}/denoiser.safetensors |
| motion_mask_mode: concat |
| num_frames_per_token: 4 |
| nframe_root_dim: 20 |
| latent_embedding_dim: 128 |
| motion_rep: |
| _target_: ardy.motion_rep.ArdyMotionRep |
| fps: 20 |
| stats_path: ${oc.select:checkpoint_dir}/stats/motion/ |
| skeleton: |
| _target_: ardy.skeleton.CoreSkeleton27 |
| llm_shape: |
| - 1 |
| - 4096 |
| use_text_mask: false |
| latent_dim: 1024 |
| ff_size: 2048 |
| num_layers: 8 |
| num_heads: 8 |
| activation: gelu |
| dropout: 0.0 |
| pe_dropout: 0.0 |
| norm_first: false |
| input_first_heading_angle: true |
| positional_encoding_mode: learned_prefix_zero_at_first_generation |
|
|
