Downloads · 30 days
21
36% of all-time downloads
MolmoAct2-BimanualYAM-oranges-12k
ASethi04/MolmoAct2-BimanualYAM-oranges-12k
MolmoAct2-BimanualYAM-oranges-12k is a robotics model from ASethi04. Use it for the robotics task on the model card, and read the license before you ship it in a product. It is set up for lerobot. The card lists the license as apache-2.0.
Fine-tune of allenai/MolmoAct2-BimanualYAM on brandonyang/yam-vive-teleop (80 teleop episodes, 74,927 frames, bimanual YAM, 30 fps) for "Put all oranges in the bowl".
All-time downloads
59
Public
Parameters
5.6B
11.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors11.5 GB · 100%
Parameter types
How the weights are stored.
BF165.4B · 97%
Base models
Datasets
Model card
From the Hugging Face model README
MolmoAct2-BimanualYAM — "Put all oranges in the bowl" (12k steps)
Fine-tune of allenai/MolmoAct2-BimanualYAM on brandonyang/yam-vive-teleop (80 teleop episodes, 74,927 frames, bimanual YAM, 30 fps) for "Put all oranges in the bowl".
Companion to ASethi04/MolmoAct2-BimanualYAM-oranges (5,000 steps). This model trains 2.4× longer and is expected to be the stronger policy.
What changed vs the 5k run
| 5k run | this model (12k) | |
|---|---|---|
| Steps / epochs | 5,000 / 4.3 | 12,000 / 10.3 |
| Action-expert LR | 1.5e-4 | 1e-4 |
| LoRA adaptation vs reference recipe | 60% | 145% |
| Expert:LoRA travel ratio | 3.0 | 2.0 (matches reference) |
| Saturation jitter | 0.5–1.5 | 0.8–1.2 |
| Hue jitter | ±0.05 | ±0.02 |
The VLM LoRA learning rate is hardcoded at 5e-5 in the training code, so adaptation on that path scales only with step count. 12,000 steps restores it to 145% of the reference recipe while keeping the expert-to-LoRA ratio at the reference's 2.0. The narrower color jitter reflects that this task is defined by locating orange objects.
| Trainable params | 727,296,544 / 5,591,928,304 (13%) |
| VLM | LoRA r=64, α=16, dropout=0.05 @ LR 5e-5 |
| Action expert | fully fine-tuned @ LR 1e-4 |
| Global batch | 64 (8 GPUs × 8) |
| Optimizer | AdamW β=(0.9,0.95), ε=1e-6, wd=0, clip 1.0 |
| Schedule | cosine, 600-step warmup, decay ratio 0.1 |
| Precision | bfloat16 + gradient checkpointing |
| Action mode | both (discrete FAST + flow matching), 8 flow timesteps |
| Chunk / executed | 30 / 30 (1 s @ 30 Hz) |
| Action space | 14-D absolute joint pose |
| Cameras | observation.images.{top,left,right} @ 480×270 |
| Normalization | quantile q01/q99; grippers raw |
| Split / seed | 100/0 (all 80 episodes) / 1000 |
Final training step: step:12K smpl:768K ep:820 epch:10.25 loss:0.665 grdn:2.058 lr:5.0e-06 updt_s:2.410 data_s:0.074 smp/s:26 mem_gb:25.86 discrete_ce_loss:0.661 discrete_z_loss:0.000 action_flow_loss:0.003
Usage notes
- Set
inference_action_mode="continuous"— the saved config hasNone. - Do not pass
norm_tag. - Task string must match training exactly:
Put all oranges in the bowl. - Consider
n_action_steps< 30 at deployment: executing all 30 open-loop means replanning at 1 Hz, which limits reactivity on a sequential multi-object task.
lerobot-policy-server \
--policy.pretrained_name_or_path=ASethi04/MolmoAct2-BimanualYAM-oranges-12k \
--policy.inference_action_mode=continuous \
--policy.model_dtype=bfloat16 --policy.device=cuda --host=0.0.0.0 --port=8081
Limitations
Single task, 80 demonstrations, no held-out validation set. Validate on hardware with a no-motion action probe before arming the robot.
- Task
- Robotics
- Library
- lerobot
- License
- apache-2.0
- Created
- Aug 5, 2026
- Updated
- Aug 5, 2026