Feature Extraction
Transformers
Safetensors
sentence-transformers
multilingual
embedding_gemma2
embedding
multimodal-embedding
multimodal
vision
audio
video
image-feature-extraction
audio-feature-extraction
video-feature-extraction
sentence-similarity
Instructions to use google/embeddinggemma-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google/embeddinggemma-2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="google/embeddinggemma-2")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModel processor = AutoProcessor.from_pretrained("google/embeddinggemma-2") model = AutoModel.from_pretrained("google/embeddinggemma-2", device_map="auto") - sentence-transformers
How to use google/embeddinggemma-2 with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("google/embeddinggemma-2") sentences = [ "The weather is lovely today.", "It's so sunny outside!", "He drove to the stadium." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] - Notebooks
- Google Colab
- Kaggle
Download config.json from google/embeddinggemma-2: direct link, hf CLI and curl.
- Browser
- Download file 4.46 kB
-
https://huggingface.co/google/embeddinggemma-2/resolve/main/config.json
- Command line
-
hf download hf://google/embeddinggemma-2/config.json
-
curl -L -o config.json https://huggingface.co/google/embeddinggemma-2/resolve/main/config.json
4.46 kB
| { | |
| "architectures": [ | |
| "EmbeddingGemma2Model" | |
| ], | |
| "audio_config": { | |
| "_name_or_path": "", | |
| "architectures": null, | |
| "attention_chunk_size": 12, | |
| "attention_context_left": 13, | |
| "attention_context_right": 0, | |
| "attention_invalid_logits_value": -1000000000.0, | |
| "attention_logit_cap": 50.0, | |
| "chunk_size_feed_forward": 0, | |
| "conv_kernel_size": 5, | |
| "dtype": "bfloat16", | |
| "gradient_clipping": 10000000000.0, | |
| "hidden_act": "silu", | |
| "hidden_size": 1024, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "initializer_range": 0.02, | |
| "is_encoder_decoder": false, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "model_type": "gemma4_audio", | |
| "num_attention_heads": 8, | |
| "num_hidden_layers": 12, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "output_proj_dims": 1536, | |
| "problem_type": null, | |
| "residual_weight": 0.5, | |
| "return_dict": true, | |
| "rms_norm_eps": 1e-06, | |
| "subsampling_conv_channels": [ | |
| 128, | |
| 32 | |
| ], | |
| "use_clipped_linears": true | |
| }, | |
| "audio_token_id": 258881, | |
| "boa_token_id": 256000, | |
| "boi_token_id": 255999, | |
| "dtype": "bfloat16", | |
| "eoa_token_index": 258883, | |
| "eoi_token_id": 258882, | |
| "image_token_id": 258880, | |
| "initializer_range": 0.02, | |
| "model_type": "embedding_gemma2", | |
| "text_config": { | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 2, | |
| "dtype": "bfloat16", | |
| "embedding_dim": 768, | |
| "eos_token_id": 1, | |
| "head_dim": 256, | |
| "hidden_activation": "gelu_pytorch_tanh", | |
| "hidden_size": 512, | |
| "hidden_size_per_layer_input": 512, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 2048, | |
| "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" | |
| ], | |
| "max_position_embeddings": 262144, | |
| "model_type": "embedding_gemma2_text", | |
| "num_attention_heads": 4, | |
| "num_hidden_layers": 24, | |
| "num_key_value_heads": 2, | |
| "pad_token_id": 0, | |
| "per_layer_config": { | |
| "05": { | |
| "head_dim": 512, | |
| "num_key_value_heads": 1 | |
| }, | |
| "11": { | |
| "head_dim": 512, | |
| "num_key_value_heads": 1 | |
| }, | |
| "17": { | |
| "head_dim": 512, | |
| "num_key_value_heads": 1 | |
| }, | |
| "23": { | |
| "head_dim": 512, | |
| "num_key_value_heads": 1 | |
| } | |
| }, | |
| "rms_norm_eps": 1e-06, | |
| "rope_parameters": { | |
| "full_attention": { | |
| "rope_theta": 1000000.0, | |
| "rope_type": "default" | |
| }, | |
| "sliding_attention": { | |
| "rope_theta": 10000.0, | |
| "rope_type": "default" | |
| } | |
| }, | |
| "sliding_window": 512, | |
| "vocab_size": 262144 | |
| }, | |
| "transformers_version": "5.18.0.dev0", | |
| "video_token_id": 258884, | |
| "vision_config": { | |
| "_name_or_path": "", | |
| "architectures": null, | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "chunk_size_feed_forward": 0, | |
| "default_output_length": 280, | |
| "dtype": "bfloat16", | |
| "global_head_dim": 64, | |
| "head_dim": 64, | |
| "hidden_activation": "gelu_pytorch_tanh", | |
| "hidden_size": 768, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "is_encoder_decoder": false, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "max_position_embeddings": 131072, | |
| "model_type": "gemma4_vision", | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 16, | |
| "num_key_value_heads": 12, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "patch_size": 16, | |
| "pooling_kernel_size": 3, | |
| "position_embedding_size": 10240, | |
| "problem_type": null, | |
| "return_dict": true, | |
| "rms_norm_eps": 1e-06, | |
| "rope_parameters": { | |
| "rope_theta": 100.0, | |
| "rope_type": "axial" | |
| }, | |
| "standardize": false, | |
| "use_clipped_linears": false | |
| }, | |
| "vision_soft_tokens_per_image": 280 | |
| } | |