| # Coda-Robotics/OpenVLA-ER-Select-Book | |
| ## Model Description | |
| This is a full fine-tuned model with LoRA weights merged into base model of OpenVLA, fine-tuned on the select_book dataset. | |
| ## Training Details | |
| - **Dataset:** select_book | |
| - **Number of Episodes:** 479 | |
| - **Batch Size:** 8 | |
| - **Training Steps:** 20000 | |
| - **Learning Rate:** 2e-5 | |
| - **LoRA Configuration:** | |
| - Rank: 32 | |
| - Dropout: 0.0 | |
| - Target Modules: all-linear | |
| ## Usage | |
| ```python | |
| from transformers import AutoProcessor, AutoModelForVision2Seq | |
| # Load the model and processor | |
| processor = AutoProcessor.from_pretrained("Coda-Robotics/OpenVLA-ER-Select-Book") | |
| model = AutoModelForVision2Seq.from_pretrained("Coda-Robotics/OpenVLA-ER-Select-Book") | |
| # Process an image | |
| image = ... # Load your image | |
| inputs = processor(images=image, return_tensors="pt") | |
| outputs = model.generate(**inputs) | |
| text = processor.decode(outputs[0], skip_special_tokens=True) | |
| ``` | |