Instructions to use vikenkd/vqa-llm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use vikenkd/vqa-llm with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("vikenkd/vqa-llm", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Delete config.json
Browse files- config.json +0 -16
config.json
DELETED
|
@@ -1,16 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"batchnorm_layer": 256,
|
| 3 |
-
"dropout": 0.3,
|
| 4 |
-
"embed_dim": 512,
|
| 5 |
-
"expansion_factor": 4,
|
| 6 |
-
"hidden_dim": 128,
|
| 7 |
-
"input_layer": 128,
|
| 8 |
-
"model_type": "vqa-llm",
|
| 9 |
-
"n_dense": 6,
|
| 10 |
-
"n_heads": 8,
|
| 11 |
-
"num_layers": 2,
|
| 12 |
-
"output_classification": 3454,
|
| 13 |
-
"output_layer": 256,
|
| 14 |
-
"transformers_version": "4.41.2",
|
| 15 |
-
"w_s": 0.5
|
| 16 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|