Instructions to use jxu124/TiO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use jxu124/TiO with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="jxu124/TiO", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("jxu124/TiO", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse filesset use_fast=False
README.md
CHANGED
|
@@ -18,7 +18,7 @@ import torch
|
|
| 18 |
import requests
|
| 19 |
|
| 20 |
# Load model, tokenizer, image_processor
|
| 21 |
-
tokenizer = AutoTokenizer.from_pretrained("jxu124/TiO")
|
| 22 |
image_processor = AutoImageProcessor.from_pretrained("jxu124/TiO")
|
| 23 |
model = AutoModel.from_pretrained("jxu124/TiO", trust_remote_code=True)
|
| 24 |
model = model.to(torch.float16).cuda() # It will be faster when using float16.
|
|
|
|
| 18 |
import requests
|
| 19 |
|
| 20 |
# Load model, tokenizer, image_processor
|
| 21 |
+
tokenizer = AutoTokenizer.from_pretrained("jxu124/TiO", use_fast=False)
|
| 22 |
image_processor = AutoImageProcessor.from_pretrained("jxu124/TiO")
|
| 23 |
model = AutoModel.from_pretrained("jxu124/TiO", trust_remote_code=True)
|
| 24 |
model = model.to(torch.float16).cuda() # It will be faster when using float16.
|