MolmoBot-Pi0-DROID-toys-absjoint-fullft

shrg7/MolmoBot-Pi0-DROID-toys-absjoint-fullft

MolmoBot-Pi0-DROID-toys-absjoint-fullft is a robotics model from shrg7. Use it for the robotics task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.

Full (action-only) fine-tune of MolmoBot-Pi0-DROID on shrg7/droid-toys, with absolute joint-position action targets.

Downloads · 30 days

Access

Public

Updated Jul 22, 2026

Parameters

3.5B

7 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors7 GB · 100%

Parameter types

How the weights are stored.

BF163.5B · 100%

Model card

From the Hugging Face model README

MolmoBot-Pi0 — DROID-toys, absolute joint, full fine-tune

Full (action-only) fine-tune of MolmoBot-Pi0-DROID on shrg7/droid-toys, with absolute joint-position action targets.

Checkpoint

Step 5000 (end of schedule), val_action_loss = 0.0079
Flat model.safetensors — loads directly into a plain PI0Pytorch
assets/ holds the norm stats; metadata.pt the run metadata
Optimizer state is not included (inference/eval only, no resume)

Training


Config	`molmobot_pi0_lerobot_droid_absjoint`
Dataset	`shrg7/droid-toys` (LeRobot v3.0) — 31 episodes / 6,952 frames @15fps
Action repr	`joint_absolute` — targets are future absolute joint positions `q[t+1]`, 8-dim (7 arm + gripper)
Action horizon	16
Cameras	`exterior_1_left` (exo) + `wrist_left`, 224×224 resize-with-pad
Trainable	everything except `vision_tower` (frozen via `freeze_filter`)
Batch	64 × 2 grad-accum = 128 effective, 4× NVIDIA L40
LR	5e-5 constant (200-step warmup; `peak_lr == decay_lr`, so the cosine is flat)
Steps	5,000 (~50 epochs), 11h25m

Validation curve

step	val_action_loss
3500	0.0096
4000	0.0086
4500	0.0085
5000	0.0079

Val loss was still descending at the end of the schedule — this checkpoint is not converged, and a longer run should improve on it.

Caveat

droid-toys is a small dataset (31 episodes). Treat this as a baseline for comparison against the LoRA counterpart (MolmoBot-Pi0-DROID-toys-absjoint-lora-r64), which was trained on the same data with the same config, not as a general-purpose policy.

Task: Robotics
License: apache-2.0
Created: Jul 22, 2026
Updated: Jul 22, 2026