Sentence Similarity
sentence-transformers
Safetensors
gemma3_text
feature-extraction
dense
Generated from Trainer
dataset_size:2609
loss:MultipleNegativesRankingLoss
Eval Results (legacy)
text-embeddings-inference
Instructions to use TextModel/Embedding-crime-indo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use TextModel/Embedding-crime-indo with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("TextModel/Embedding-crime-indo") sentences = [ "query: Kalau si koruptor ternyata udah nggak punya harta lagi buat bayar uang pengganti, apa konsekuensinya?", "passage: Hukumnya adalah tindak pidana yang diancam dengan pidana penjara paling lama 4 tahun atau pidana denda paling banyak kategori IV karena menggunakan ancaman kekerasan. (Pasal 302 KUHP)", "passage: Kalau harta bendanya tidak mencukupi, terpidana bisa dipidana penjara yang lamanya tidak melebihi ancaman maksimum pidana pokoknya dan sudah ditentukan langsung di dalam putusan pengadilan.", "passage: Penyitaan dan pelelangan harta bila uang pengganti tidak dibayar." ] 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, | |
| "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_parameters": { | |
| "full_attention": { | |
| "rope_theta": 1000000.0, | |
| "rope_type": "default" | |
| }, | |
| "sliding_attention": { | |
| "rope_theta": 10000.0, | |
| "rope_type": "default" | |
| } | |
| }, | |
| "sliding_window": 257, | |
| "tie_word_embeddings": true, | |
| "transformers_version": "5.0.0", | |
| "use_bidirectional_attention": true, | |
| "use_cache": true, | |
| "vocab_size": 262144 | |
| } | |