Sentence Similarity
sentence-transformers
ONNX
English
gemma3_text
embeddings
embeddinggemma-tuning-lab
sift
chrome-extension
text-embeddings-inference
Instructions to use shreyask/sift-finetuned with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use shreyask/sift-finetuned with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("shreyask/sift-finetuned") 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
| { | |
| "_sliding_window_pattern": 6, | |
| "architectures": [ | |
| "Gemma3TextModel" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "attn_logit_softcapping": null, | |
| "bos_token_id": 2, | |
| "dtype": "float32", | |
| "eos_token_id": 1, | |
| "export_model_type": "transformer", | |
| "final_logit_softcapping": null, | |
| "head_dim": 256, | |
| "hidden_activation": "gelu_pytorch_tanh", | |
| "hidden_size": 768, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 1152, | |
| "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": 2048, | |
| "model_type": "gemma3_text", | |
| "num_attention_heads": 3, | |
| "num_hidden_layers": 24, | |
| "num_key_value_heads": 1, | |
| "pad_token_id": 0, | |
| "query_pre_attn_scalar": 256, | |
| "rms_norm_eps": 1e-06, | |
| "rope_local_base_freq": 10000.0, | |
| "rope_scaling": null, | |
| "rope_theta": 1000000.0, | |
| "sliding_window": 129, | |
| "transformers_version": "4.57.6", | |
| "use_bidirectional_attention": true, | |
| "use_cache": true, | |
| "vocab_size": 262144 | |
| } | |