Instructions to use namdp-ptit/ViDense with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use namdp-ptit/ViDense with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, ViDense tokenizer = AutoTokenizer.from_pretrained("namdp-ptit/ViDense") model = ViDense.from_pretrained("namdp-ptit/ViDense", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download 1_Pooling/config.json from namdp-ptit/ViDense: direct link, hf CLI and curl.
- Browser
- Download file 191 Bytes
-
https://huggingface.co/namdp-ptit/ViDense/resolve/main/1_Pooling/config.json
- Command line
-
hf download hf://namdp-ptit/ViDense/1_Pooling/config.json
-
curl -L -o config.json https://huggingface.co/namdp-ptit/ViDense/resolve/main/1_Pooling/config.json
191 Bytes
| { | |
| "word_embedding_dimension": 1024, | |
| "pooling_mode_cls_token": false, | |
| "pooling_mode_mean_tokens": true, | |
| "pooling_mode_max_tokens": false, | |
| "pooling_mode_mean_sqrt_len_tokens": false | |
| } |