Sentence Similarity
sentence-transformers
Safetensors
English
embedding_gemma2
audio
music
music-information-retrieval
text-to-audio-retrieval
embeddings
Instructions to use jaisawhney/SonicEmbed with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use jaisawhney/SonicEmbed with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("jaisawhney/SonicEmbed") sentences = [ "That is a happy person", "That is a happy dog", "That is a very happy person", "Today is a sunny day" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle
Download config.json from jaisawhney/SonicEmbed: direct link, hf CLI and curl.
- Browser
- Download file 2.98 kB
-
https://huggingface.co/jaisawhney/SonicEmbed/resolve/main/config.json
- Command line
-
hf download hf://jaisawhney/SonicEmbed/config.json
-
curl -L -o config.json https://huggingface.co/jaisawhney/SonicEmbed/resolve/main/config.json
2.98 kB
| { | |
| "architectures": [ | |
| "EmbeddingGemma2Model" | |
| ], | |
| "audio_config": { | |
| "attention_chunk_size": 12, | |
| "attention_context_left": 13, | |
| "attention_context_right": 0, | |
| "attention_invalid_logits_value": -1000000000.0, | |
| "attention_logit_cap": 50.0, | |
| "conv_kernel_size": 5, | |
| "dtype": "float32", | |
| "gradient_clipping": 10000000000.0, | |
| "hidden_act": "silu", | |
| "hidden_size": 1024, | |
| "initializer_range": 0.02, | |
| "model_type": "gemma4_audio", | |
| "num_attention_heads": 8, | |
| "num_hidden_layers": 12, | |
| "output_proj_dims": 1536, | |
| "residual_weight": 0.5, | |
| "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": "float32", | |
| "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": "float32", | |
| "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": "5.20.2", | |
| "video_token_id": 258884, | |
| "vision_config": null, | |
| "vision_soft_tokens_per_image": 280 | |
| } | |