Video-Text-to-Text
Transformers
Safetensors
English
molmo2
image-text-to-text
multimodal
olmo
molmo
custom_code
4-bit precision
bitsandbytes
Instructions to use Cycl0/Molmo2-VideoPoint-4B-bnb-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Cycl0/Molmo2-VideoPoint-4B-bnb-4bit with Transformers:
# Load model directly from transformers import AutoModelForImageTextToText model = AutoModelForImageTextToText.from_pretrained("Cycl0/Molmo2-VideoPoint-4B-bnb-4bit", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
File size: 301 Bytes
5953f6d | 1 2 3 4 5 6 7 8 9 10 11 12 | {
"auto_map": {
"AutoProcessor": "processing_molmo2.Molmo2Processor"
},
"image_use_col_tokens": true,
"processor_class": "Molmo2Processor",
"use_frame_special_tokens": false,
"use_single_crop_col_tokens": false,
"use_single_crop_start_token": true,
"video_use_col_tokens": false
}
|