Visual Question Answering
Transformers
English
videollama2_mistral
text-generation
multimodal large language model
large video-language model
Instructions to use DAMO-NLP-SG/VideoLLaMA2-7B-16F-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use DAMO-NLP-SG/VideoLLaMA2-7B-16F-Base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("visual-question-answering", model="DAMO-NLP-SG/VideoLLaMA2-7B-16F-Base")# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("DAMO-NLP-SG/VideoLLaMA2-7B-16F-Base", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Zesen Cheng commited on
Update config.json
Browse files- config.json +1 -1
config.json
CHANGED
|
@@ -21,7 +21,7 @@
|
|
| 21 |
"mm_vision_select_feature": "patch",
|
| 22 |
"mm_vision_select_layer": -2,
|
| 23 |
"mm_vision_tower": "openai/clip-vit-large-patch14-336",
|
| 24 |
-
"model_type": "
|
| 25 |
"num_attention_heads": 32,
|
| 26 |
"num_frames": 16,
|
| 27 |
"num_hidden_layers": 32,
|
|
|
|
| 21 |
"mm_vision_select_feature": "patch",
|
| 22 |
"mm_vision_select_layer": -2,
|
| 23 |
"mm_vision_tower": "openai/clip-vit-large-patch14-336",
|
| 24 |
+
"model_type": "videollama2_mistral",
|
| 25 |
"num_attention_heads": 32,
|
| 26 |
"num_frames": 16,
|
| 27 |
"num_hidden_layers": 32,
|