Sentence Similarity
sentence-transformers
Safetensors
Transformers
French
English
Bilingual
feature-extraction
french
english
sentence-embedding
mteb
custom_code
Eval Results (legacy)
Instructions to use dangvantuan/french-document-embedding with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use dangvantuan/french-document-embedding with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("dangvantuan/french-document-embedding", trust_remote_code=True) sentences = [ "C'est une personne heureuse", "C'est un chien heureux", "C'est une personne très heureuse", "Aujourd'hui est une journée ensoleillée" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Transformers
How to use dangvantuan/french-document-embedding with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("dangvantuan/french-document-embedding", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "_name_or_path": "dangvantuan/bilingual_impl", | |
| "architectures": [ | |
| "BilingualModel" | |
| ], | |
| "attention_probs_dropout_prob": 0.0, | |
| "auto_map": { | |
| "AutoConfig": "dangvantuan/bilingual_impl--configuration.BilingualConfig", | |
| "AutoModel": "dangvantuan/bilingual_impl--modelling.BilingualModel", | |
| "AutoModelForMaskedLM": "dangvantuan/bilingual_impl--modelling.BilingualForMaskedLM", | |
| "AutoModelForMultipleChoice": "dangvantuan/bilingual_impl--modelling.BilingualForMultipleChoice", | |
| "AutoModelForQuestionAnswering": "dangvantuan/bilingual_impl--modelling.BilingualForQuestionAnswering", | |
| "AutoModelForSequenceClassification": "dangvantuan/bilingual_impl--modelling.BilingualForSequenceClassification", | |
| "AutoModelForTokenClassification": "dangvantuan/bilingual_impl--modelling.BilingualForTokenClassification" | |
| }, | |
| "classifier_dropout": 0.0, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 768, | |
| "id2label": { | |
| "0": "LABEL_0" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "label2id": { | |
| "LABEL_0": 0 | |
| }, | |
| "layer_norm_eps": 1e-12, | |
| "layer_norm_type": "layer_norm", | |
| "logn_attention_clip1": false, | |
| "logn_attention_scale": false, | |
| "max_position_embeddings": 8192, | |
| "model_type": "Bilingual", | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 12, | |
| "pack_qkv": true, | |
| "pad_token_id": 1, | |
| "position_embedding_type": "rope", | |
| "rope_scaling": { | |
| "factor": 8.0, | |
| "type": "ntk" | |
| }, | |
| "rope_theta": 20000, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.42.3", | |
| "type_vocab_size": 1, | |
| "unpad_inputs": false, | |
| "use_memory_efficient_attention": false, | |
| "vocab_size": 250048 | |
| } |