Video-Text-to-Text
Transformers
Safetensors
English
Chinese
moss_vl
feature-extraction
MOSS-VL
realtime
streaming
video-understanding
FP8
compressed-tensors
HQQ
quantized
custom_code
Instructions to use OpenMOSS-Team/MOSS-VL-Realtime-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use OpenMOSS-Team/MOSS-VL-Realtime-FP8 with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("OpenMOSS-Team/MOSS-VL-Realtime-FP8", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
| default_stage: | |
| default_modifiers: | |
| QuantizationModifier: | |
| targets: ['re:^model\.language_model\.layers\.(0|1|3|4|5|7|8|9|11|12|13|15|16|17|19|20|21|23|24|25|27|28|29|31|32|33|35|36|37|39|40|41|43|44|45|47)\.(self_attn\.(q_proj|k_proj|v_proj|o_proj)|mlp\.(gate_proj|up_proj|down_proj))$'] | |
| ignore: [] | |
| scheme: FP8_DYNAMIC | |
| bypass_divisibility_checks: false | |