Visual Question Answering
Transformers
Safetensors
English
videollama2_mistral
text-generation
multimodal large language model
large video-language model
Instructions to use Aliayub1995/VideoLLaMA2-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Aliayub1995/VideoLLaMA2-7B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("visual-question-answering", model="Aliayub1995/VideoLLaMA2-7B")# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("Aliayub1995/VideoLLaMA2-7B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update videollama2/__init__.py
Browse files- videollama2/__init__.py +1 -1
videollama2/__init__.py
CHANGED
|
@@ -33,7 +33,7 @@ def model_init(model_path=None, **kwargs):
|
|
| 33 |
return model, processor, tokenizer
|
| 34 |
|
| 35 |
|
| 36 |
-
def mm_infer(
|
| 37 |
"""inference api of VideoLLaMA2 for video understanding.
|
| 38 |
|
| 39 |
Args:
|
|
|
|
| 33 |
return model, processor, tokenizer
|
| 34 |
|
| 35 |
|
| 36 |
+
def mm_infer(image_or_video, instruct, model, tokenizer, modal='video', **kwargs):
|
| 37 |
"""inference api of VideoLLaMA2 for video understanding.
|
| 38 |
|
| 39 |
Args:
|