pi0fast-dk1-lora-v1

Kavin60606/pi0fast-dk1-lora-v1

pi0fast-dk1-lora-v1 is a robotics model from Kavin60606. 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.

Fine-tuned pi0-FAST on egocentric manipulation data for the TRLC DK1 Follower robot arm.

Downloads · 30 days

Access

Public

Updated Apr 30, 2026

Repo size

8.6 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

Other8.6 GB · 100%

At a glance

Task: Robotics
License: apache-2.0
Access: Public
Created: Apr 29, 2026
Updated: Apr 30, 2026
SHA: b431e62e

Base models

physical-intelligence/pi0-fast

Model card

From the Hugging Face model README

pi0-FAST DK1 LoRA Fine-tune v1

Fine-tuned pi0-FAST on egocentric manipulation data for the TRLC DK1 Follower robot arm.

Training Details

Parameter	Value
Base model	pi0-FAST (PaliGemma 2B LoRA)
Fine-tune method	LoRA (gemma_2b_lora)
Steps	1000
Batch size	32
Action dim	7 (6 arm joints + 1 gripper)
Action horizon	10
Max token length	350
delta joint actions	True

Dataset

Field	Value
HF Dataset	kavinrajkr60/dk1_egodex
Source	EgoDex egocentric manipulation episodes
Episodes	1800 (enriched ego part1 + part2)
Annotations	L1-L5 language annotations
FPS	10
Robot	TRLC DK1 Follower (6-DOF + parallel jaw gripper)

Robot: TRLC DK1 Follower

6-DOF revolute arm + 2 prismatic gripper joints
End effector: tool0
IK solver: PINK (Pinocchio, QP-based differential IK)
Action space: 7-dim [joint1..joint6, gripper_open]

Loss Curve

Step 0: loss=12.56
Step 300-360: loss=3.21-3.38
Step 1000: training complete (~55 min, single GPU)

Loss dropped from 12.56 to ~3.2 over 1000 steps.

W&B Run

https://wandb.ai/kavinrajkr60-dsfsd/roboinc/runs/22za2p1i

Known Issues

Token truncation: some samples exceed max_token_len=350 (up to 414 tokens). Increase in next run.

Task: Robotics
License: apache-2.0
Created: Apr 29, 2026
Updated: Apr 30, 2026