Downloads · 30 days
0
ftp1_univtac_finetune
MJJJJ1064/ftp1_univtac_finetune
ftp1_univtac_finetune is a machine learning model from MJJJJ1064. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
ftp1univtacfinetune is the UniVTAC fine-tuned release of FTP-1. It contains task-specific checkpoints initialized from the FTP-1 pretrained model and further trained on UniVTAC tasks.
Access
Public
Updated Jun 13, 2026
Repo size
49.5 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors49.5 GB · 100%
At a glance
- Access
- Public
- Created
- Jun 12, 2026
- Updated
- Jun 13, 2026
- SHA
- 620ac69b
Model card
From the Hugging Face model README
FTP-1 UniVTAC Finetune
ftp1_univtac_finetune is the UniVTAC fine-tuned release of FTP-1. It contains task-specific checkpoints initialized from the FTP-1 pretrained model and further trained on UniVTAC tasks.
This release currently includes 6 task checkpoints:
FTP1_UniVTAC_insert_hole_expert_gsmall_ftp1FTP1_UniVTAC_insert_tube_expert_gsmall_ftp1FTP1_UniVTAC_lift_bottle_expert_gsmall_ftp1FTP1_UniVTAC_lift_can_expert_gsmall_ftp1FTP1_UniVTAC_pull_out_key_expert_gsmall_ftp1FTP1_UniVTAC_put_bottle_expert_gsmall_ftp1
Each task directory contains a fine-tuned checkpoint at step 19999.
Notes
- Type: fine-tuned checkpoint collection
- Base model:
ftp1_pretrain_v0426_50kstep - Domain: UniVTAC
- Use: task-specific inference or further adaptation
Links
- Project homepage: https://ftp1-policy.github.io/
- Open-source repository: https://github.com/michaelyuancb/ftp1-policy
- Pretrained checkpoints: https://huggingface.co/datasets/MJJJJ1064/ftp1_v0426_50kstep or https://www.modelscope.cn/models/michaelyuancb/ftp1_v0426_50kstep
- Created
- Jun 12, 2026
- Updated
- Jun 13, 2026