Any-to-Any
Transformers
Safetensors
PEFT
PyTorch
English
molmo
text-generation
molmo-audio
multimodal
audio-text-to-text
image-text-to-text
audio
speech
diarization
vllm
blaster
cc-by-nc-sa-4.0
custom_code
Instructions to use 0x8badbeef/molmo-audio-serving-diar-d with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use 0x8badbeef/molmo-audio-serving-diar-d with Transformers:
# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("0x8badbeef/molmo-audio-serving-diar-d", trust_remote_code=True, device_map="auto") - PEFT
How to use 0x8badbeef/molmo-audio-serving-diar-d with PEFT:
Task type is invalid.
- Notebooks
- Google Colab
- Kaggle
File size: 634 Bytes
476a0f2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 | {
"auto_map": {
"AutoImageProcessor": "image_preprocessing_molmo.MolmoImageProcessor",
"AutoProcessor": "preprocessing_molmo.MolmoProcessor"
},
"base_image_input_size": [
336,
336
],
"do_normalize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_padding_mask": true,
"image_patch_size": 14,
"image_processor_type": "MolmoImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"image_token_length_h": 12,
"image_token_length_w": 12,
"max_crops": 12,
"overlap_margins": [
4,
4
],
"processor_class": "MolmoProcessor"
}
|