Instructions to use julia225/egoblind-ra-sft-vision with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use julia225/egoblind-ra-sft-vision with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("moonshotai/Kimi-VL-A3B-Instruct") model = PeftModel.from_pretrained(base_model, "julia225/egoblind-ra-sft-vision") - Notebooks
- Google Colab
- Kaggle
| { | |
| "auto_map": { | |
| "AutoImageProcessor": "image_processing_kimi_vl.KimiVLImageProcessor", | |
| "AutoProcessor": "processing_kimi_vl.KimiVLProcessor" | |
| }, | |
| "image_mean": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "image_processor_type": "KimiVLImageProcessor", | |
| "image_std": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "in_token_limit": 4096, | |
| "merge_kernel_size": [ | |
| 2, | |
| 2 | |
| ], | |
| "num_pooled_tokens": 1024, | |
| "pad_input": true, | |
| "patch_size": 14, | |
| "processor_class": "KimiVLProcessor" | |
| } | |