Instructions to use Jiqing/tiny-random-tvp with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Jiqing/tiny-random-tvp with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, TvpForVideoGrounding processor = AutoProcessor.from_pretrained("Jiqing/tiny-random-tvp") model = TvpForVideoGrounding.from_pretrained("Jiqing/tiny-random-tvp", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update config.json
Browse files- config.json +2 -2
config.json
CHANGED
|
@@ -50,9 +50,9 @@
|
|
| 50 |
"max_text_length": 20,
|
| 51 |
"model_type": "tvp",
|
| 52 |
"num_attention_heads": 4,
|
| 53 |
-
"
|
| 54 |
"num_hidden_layers": 4,
|
| 55 |
-
"
|
| 56 |
"pad_token_id": 0,
|
| 57 |
"position_embedding_type": "absolute",
|
| 58 |
"torch_dtype": "float32",
|
|
|
|
| 50 |
"max_text_length": 20,
|
| 51 |
"model_type": "tvp",
|
| 52 |
"num_attention_heads": 4,
|
| 53 |
+
"num_frames": 1,
|
| 54 |
"num_hidden_layers": 4,
|
| 55 |
+
"visual_prompt_size": 96,
|
| 56 |
"pad_token_id": 0,
|
| 57 |
"position_embedding_type": "absolute",
|
| 58 |
"torch_dtype": "float32",
|