Visual Document Retrieval
Transformers
Safetensors
gemma3
image-text-to-text
vision-language
retrieval
multimodal
multilingual
document-retrieval
matryoshka-embeddings
dense-retrieval
22-languages
Eval Results (legacy)
text-generation-inference
Instructions to use Cognitive-Lab/NetraEmbed with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Cognitive-Lab/NetraEmbed with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForImageTextToText processor = AutoProcessor.from_pretrained("Cognitive-Lab/NetraEmbed") model = AutoModelForImageTextToText.from_pretrained("Cognitive-Lab/NetraEmbed") - Notebooks
- Google Colab
- Kaggle
| { | |
| "architectures": [ | |
| "Gemma3ForConditionalGeneration" | |
| ], | |
| "boi_token_index": 255999, | |
| "dtype": "bfloat16", | |
| "eoi_token_index": 256000, | |
| "eos_token_id": [ | |
| 1, | |
| 106 | |
| ], | |
| "image_token_index": 262144, | |
| "initializer_range": 0.02, | |
| "mm_tokens_per_image": 256, | |
| "model_type": "gemma3", | |
| "text_config": { | |
| "_sliding_window_pattern": 6, | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "attn_logit_softcapping": null, | |
| "dtype": "bfloat16", | |
| "final_logit_softcapping": null, | |
| "head_dim": 256, | |
| "hidden_activation": "gelu_pytorch_tanh", | |
| "hidden_size": 2560, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 10240, | |
| "layer_types": [ | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention" | |
| ], | |
| "max_position_embeddings": 131072, | |
| "model_type": "gemma3_text", | |
| "num_attention_heads": 8, | |
| "num_hidden_layers": 34, | |
| "num_key_value_heads": 4, | |
| "query_pre_attn_scalar": 256, | |
| "rms_norm_eps": 1e-06, | |
| "rope_local_base_freq": 10000.0, | |
| "rope_scaling": { | |
| "factor": 8.0, | |
| "rope_type": "linear" | |
| }, | |
| "rope_theta": 1000000.0, | |
| "sliding_window": 1024, | |
| "use_bidirectional_attention": false, | |
| "use_cache": true, | |
| "vocab_size": 262208 | |
| }, | |
| "transformers_version": "4.57.1", | |
| "vision_config": { | |
| "attention_dropout": 0.0, | |
| "dtype": "bfloat16", | |
| "hidden_act": "gelu_pytorch_tanh", | |
| "hidden_size": 1152, | |
| "image_size": 896, | |
| "intermediate_size": 4304, | |
| "layer_norm_eps": 1e-06, | |
| "model_type": "siglip_vision_model", | |
| "num_attention_heads": 16, | |
| "num_channels": 3, | |
| "num_hidden_layers": 27, | |
| "patch_size": 14, | |
| "vision_use_head": false | |
| } | |
| } | |