Downloads · 30 days
0
lingbot-vla-v2-6b-robotwin
robbyant/lingbot-vla-v2-6b-robotwin
lingbot-vla-v2-6b-robotwin is a machine learning model from robbyant. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
LingBot-VLA-V2 is a practical Vision-Language-Action foundation model designed to move from large-scale pre-training toward reliable real-world robot applications. <p align="center" <img src="assets/lingbotvla2framewo…
Access
Public
Updated Jul 24, 2026
Repo size
25.5 GB
Likes
7
Public
Repo makeup
Click a slice to open those files.
.safetensors25.5 GB · 100%
At a glance
- Access
- Public
- Created
- Jul 24, 2026
- Updated
- Jul 24, 2026
- SHA
- 04518557
Model card
From the Hugging Face model README
LingBot-VLA-V2: From Foundation to Application
LingBot-VLA-V2 is a practical Vision-Language-Action foundation model designed to move from large-scale pre-training toward reliable real-world robot applications.
<p align="center"> <img src="assets/lingbot_vla2_framework.png" width="100%"> </p>Performance on RoboTwin 2.0
| Task | Clean | Rand |
|---|---|---|
adjust_bottle | 100% | 99% |
beat_block_hammer | 96% | 89% |
blocks_ranking_rgb | 91% | 88% |
blocks_ranking_size | 84% | 78% |
click_alarmclock | 84% | 69% |
click_bell | 91% | 81% |
dump_bin_bigbin | 97% | 94% |
grab_roller | 100% | 100% |
handover_block | 99% | 92% |
handover_mic | 99% | 98% |
hanging_mug | 49% | 49% |
lift_pot | 100% | 100% |
move_can_pot | 98% | 96% |
move_pillbottle_pad | 97% | 100% |
move_playingcard_away | 100% | 100% |
move_stapler_pad | 84% | 84% |
open_laptop | 98% | 100% |
open_microwave | 99% | 99% |
pick_diverse_bottles | 86% | 86% |
pick_dual_bottles | 96% | 98% |
place_a2b_left | 93% | 93% |
place_a2b_right | 96% | 93% |
place_bread_basket | 92% | 89% |
place_bread_skillet | 87% | 88% |
place_burger_fries | 99% | 98% |
place_can_basket | 85% | 75% |
place_cans_plasticbox | 95% | 98% |
place_container_plate | 100% | 100% |
place_dual_shoes | 96% | 99% |
place_empty_cup | 100% | 100% |
place_fan | 99% | 94% |
place_mouse_pad | 94% | 94% |
place_object_basket | 87% | 94% |
place_object_scale | 97% | 94% |
place_object_stand | 99% | 99% |
place_phone_stand | 91% | 100% |
place_shoe | 99% | 99% |
press_stapler | 98% | 99% |
put_bottles_dustbin | 89% | 94% |
put_object_cabinet | 92% | 97% |
rotate_qrcode | 92% | 92% |
scan_object | 98% | 96% |
shake_bottle | 100% | 99% |
shake_bottle_horizontally | 100% | 99% |
stack_blocks_three | 100% | 93% |
stack_blocks_two | 100% | 99% |
stack_bowls_three | 86% | 87% |
stack_bowls_two | 98% | 95% |
stamp_seal | 86% | 96% |
turn_switch | 80% | 87% |
| Avg | 93.52% | 92.80% |
Related Models
| Model Name | Huggingface | ModelScope |
|---|---|---|
| LingBot-VLA-V2 | 🤗 lingbot-vla-v2-6b | 🤖 lingbot-vla-v2-6b |
Model Sources
- Paper: From Foundation to Application: Improving VLA Models in Practice
- Repository: https://github.com/robbyant/lingbot-vla-v2
- Project Page: https://technology.robbyant.com/lingbot-vla-v2
License Agreement
This project is licensed under the Apache-2.0 License.
- Created
- Jul 24, 2026
- Updated
- Jul 24, 2026