Downloads · 30 days
5
16% of all-time downloads
kuroll/motus_vla_arena
motus_vla_arena is a machine learning model from kuroll. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
- batchsize 为单卡 batch size;采用8卡h100,总 batch size 为 32。
Downloads · 30 days
5
16% of all-time downloads
All-time downloads
31
Public
Repo size
103 GB
Likes
0
Public
Click a slice to open those files.
.pt86.8 GB · 84%
From the Hugging Face model README
| Key | Value |
|---|---|
action_dim | 7 |
state_dim | 8 |
num_video_frames | 8 |
video_height | 384 |
video_width | 320 |
global_downsample_rate | 1 |
video_action_freq_ratio | 6 |
| Key | Value |
|---|---|
type | lerobot |
max_episodes | null |
image_aug | false |
task_mode | single |
task_name | null |
params.repo_id | vla_arena |
params.embodiment_type | vla_arena |
params.enable_t5_fallback | true |
params.t5_folder_name | t5_embedding |
params.t5_text_len | 512 |
| Key | Value |
|---|---|
wan.precision | bfloat16 |
vlm.precision | bfloat16 |
vlm.frozen | true |
action_expert.hidden_size | 1024 |
action_expert.ffn_dim_multiplier | 4 |
action_expert.norm_eps | 0.00001 |
und_expert.hidden_size | 512 |
und_expert.ffn_dim_multiplier | 4 |
und_expert.norm_eps | 0.00001 |
und_expert.vlm.input_dim | 2048 |
und_expert.vlm.projector_type | mlp3x_silu |
time_distribution.timestep_sample_method | logit_normal |
time_distribution.sigmoid_scale | 1.0 |
time_distribution.min_t | 0.0 |
time_distribution.max_t | 1.0 |
inference.num_inference_timesteps | 10 |
loss_weights.video_loss_weight | 1.0 |
loss_weights.action_loss_weight | 1.0 |
ema.enabled | false |
ema.update_after_step | 0 |
ema.inv_gamma | 1.0 |
ema.power | 0.75 |
ema.min_value | 0.0 |
ema.max_value | 0.9999 |
| Key | Value |
|---|---|
batch_size | 4 |
max_steps | 45000 |
learning_rate | 2.0e-5 |
weight_decay | 0.01 |
scheduler_type | linear |
warmup_steps | 500 |
cycle_length | 45000 |
f_max | 0.99 |
f_min | 0.4 |
grad_clip_norm | 0.5 |
use_amp | true |
find_unused_parameters | false |
| Key | Value |
|---|---|
system.val_interval | 1000 |
system.num_workers | 16 |
system.pin_memory | true |
batch_size 为单卡 batch size;采用8卡h100,总 batch size 为 32。