Feature Extraction
Transformers
Safetensors
avito_gated_fusion
siglip
siglip2
vision
text
clip
multimodal
image-text-embeddings
pet-recognition
custom_code
Instructions to use AvitoTech/SigLIP2-giant-e5small-v2-gating with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use AvitoTech/SigLIP2-giant-e5small-v2-gating with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="AvitoTech/SigLIP2-giant-e5small-v2-gating", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("AvitoTech/SigLIP2-giant-e5small-v2-gating", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "model_type": "avito_gated_fusion", | |
| "architectures": [ | |
| "AvitoGatedFusionModel" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_avito_gated.AvitoGatedFusionConfig", | |
| "AutoModel": "modeling_avito_gated.AvitoGatedFusionModel" | |
| }, | |
| "embedding_dim": 512, | |
| "gate_hidden_dim": 128, | |
| "siglip_config": { | |
| "initializer_factor": 1.0, | |
| "model_type": "siglip", | |
| "text_config": { | |
| "vocab_size": 256000, | |
| "hidden_size": 1152, | |
| "intermediate_size": 4304, | |
| "num_hidden_layers": 27, | |
| "num_attention_heads": 16, | |
| "max_position_embeddings": 64, | |
| "layer_norm_eps": 1e-06, | |
| "hidden_act": "gelu_pytorch_tanh", | |
| "attention_dropout": 0.0, | |
| "projection_size": 1536, | |
| "model_type": "siglip_text_model" | |
| }, | |
| "vision_config": { | |
| "hidden_size": 1536, | |
| "intermediate_size": 6144, | |
| "num_hidden_layers": 40, | |
| "num_attention_heads": 16, | |
| "num_channels": 3, | |
| "patch_size": 16, | |
| "image_size": 384, | |
| "attention_dropout": 0.0, | |
| "layer_norm_eps": 1e-06, | |
| "hidden_act": "gelu_pytorch_tanh", | |
| "model_type": "siglip_vision_model" | |
| } | |
| }, | |
| "text_config": { | |
| "pad_token_id": 0, | |
| "model_type": "bert", | |
| "vocab_size": 30522, | |
| "hidden_size": 384, | |
| "num_hidden_layers": 12, | |
| "num_attention_heads": 12, | |
| "hidden_act": "gelu", | |
| "intermediate_size": 1536, | |
| "hidden_dropout_prob": 0.1, | |
| "attention_probs_dropout_prob": 0.1, | |
| "max_position_embeddings": 512, | |
| "type_vocab_size": 2, | |
| "initializer_range": 0.02, | |
| "layer_norm_eps": 1e-12, | |
| "position_embedding_type": "absolute", | |
| "use_cache": true, | |
| "classifier_dropout": null | |
| }, | |
| "dtype": "float32" | |
| } | |