Instructions to use visualjoyce/transformers4vl-vilbert with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use visualjoyce/transformers4vl-vilbert with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("visualjoyce/transformers4vl-vilbert", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download bert_base_6layer_6conect.json from visualjoyce/transformers4vl-vilbert: direct link, hf CLI and curl.
- Browser
- Download file 824 Bytes
-
https://huggingface.co/visualjoyce/transformers4vl-vilbert/resolve/main/bert_base_6layer_6conect.json
- Command line
-
hf download hf://visualjoyce/transformers4vl-vilbert/bert_base_6layer_6conect.json
-
curl -L -o bert_base_6layer_6conect.json https://huggingface.co/visualjoyce/transformers4vl-vilbert/resolve/main/bert_base_6layer_6conect.json
824 Bytes
| { | |
| "attention_probs_dropout_prob": 0.1, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 768, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "max_position_embeddings": 512, | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 12, | |
| "type_vocab_size": 2, | |
| "vocab_size": 30522, | |
| "v_feature_size": 2048, | |
| "v_target_size": 1601, | |
| "v_hidden_size": 1024, | |
| "v_num_hidden_layers":6, | |
| "v_num_attention_heads":8, | |
| "v_intermediate_size":1024, | |
| "bi_hidden_size":1024, | |
| "bi_num_attention_heads":8, | |
| "bi_intermediate_size": 1024, | |
| "bi_attention_type":1, | |
| "v_attention_probs_dropout_prob":0.1, | |
| "v_hidden_act":"gelu", | |
| "v_hidden_dropout_prob":0.1, | |
| "v_initializer_range":0.02, | |
| "v_biattention_id":[0, 1, 2, 3, 4, 5], | |
| "t_biattention_id":[6, 7, 8, 9, 10, 11], | |
| "pooling_method": "mul" | |
| } | |