Instructions to use 99spokes/autotrain-vit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use 99spokes/autotrain-vit with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="99spokes/autotrain-vit") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")# pip install -U transformers accelerate # Load model directly from transformers import AutoImageProcessor, AutoModelForImageClassification processor = AutoImageProcessor.from_pretrained("99spokes/autotrain-vit") model = AutoModelForImageClassification.from_pretrained("99spokes/autotrain-vit", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download training_params.json from 99spokes/autotrain-vit: direct link, hf CLI and curl.
- Browser
- Download file 813 Bytes
-
https://huggingface.co/99spokes/autotrain-vit/resolve/main/training_params.json
- Command line
-
hf download hf://99spokes/autotrain-vit/training_params.json
-
curl -L -o training_params.json https://huggingface.co/99spokes/autotrain-vit/resolve/main/training_params.json
813 Bytes
| { | |
| "data_path": "99spokes/autotrain-data-autotrain-vit", | |
| "model": "google/vit-base-patch16-384", | |
| "username": "99spokes", | |
| "lr": 5e-05, | |
| "epochs": 3, | |
| "batch_size": 8, | |
| "warmup_ratio": 0.1, | |
| "gradient_accumulation": 1, | |
| "optimizer": "adamw_torch", | |
| "scheduler": "linear", | |
| "weight_decay": 0.0, | |
| "max_grad_norm": 1.0, | |
| "seed": 42, | |
| "train_split": "train", | |
| "valid_split": "validation", | |
| "logging_steps": -1, | |
| "project_name": "/tmp/model", | |
| "auto_find_batch_size": false, | |
| "mixed_precision": "fp16", | |
| "save_total_limit": 1, | |
| "save_strategy": "epoch", | |
| "push_to_hub": true, | |
| "repo_id": "99spokes/autotrain-vit", | |
| "evaluation_strategy": "epoch", | |
| "image_column": "autotrain_image", | |
| "target_column": "autotrain_label", | |
| "log": "none" | |
| } |