Instructions to use AAyano/oft_setting1_chunksize25_batch32_30k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use AAyano/oft_setting1_chunksize25_batch32_30k with Transformers:
# Load model directly from transformers import AutoModelForVision2Seq model = AutoModelForVision2Seq.from_pretrained("AAyano/oft_setting1_chunksize25_batch32_30k", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README for _30k rename
Browse files
README.md
CHANGED
|
@@ -10,9 +10,9 @@ tags:
|
|
| 10 |
library_name: transformers
|
| 11 |
---
|
| 12 |
|
| 13 |
-
#
|
| 14 |
|
| 15 |
-
OpenVLA-OFT checkpoint fine-tuned on real-world XArm data, **setting 1: pick cube and place into plastic cup**.
|
| 16 |
LoRA weights (rank 32) are already merged into the [openvla/openvla-7b](https://huggingface.co/openvla/openvla-7b) base — this repo is a standalone model.
|
| 17 |
|
| 18 |
## Training
|
|
|
|
| 10 |
library_name: transformers
|
| 11 |
---
|
| 12 |
|
| 13 |
+
# oft_setting1_chunksize25_batch32_30k
|
| 14 |
|
| 15 |
+
**Final checkpoint at 30000 / 30000 training steps.** OpenVLA-OFT checkpoint fine-tuned on real-world XArm data, **setting 1: pick cube and place into plastic cup**.
|
| 16 |
LoRA weights (rank 32) are already merged into the [openvla/openvla-7b](https://huggingface.co/openvla/openvla-7b) base — this repo is a standalone model.
|
| 17 |
|
| 18 |
## Training
|