dangvantuan/french-document-embedding
141.6k
1{2 "_name_or_path": "dangvantuan/bilingual_impl",3 "architectures": [4 "BilingualModel"5 ],6 "attention_probs_dropout_prob": 0.0,7 "auto_map": {8 "AutoConfig": "dangvantuan/bilingual_impl--configuration.BilingualConfig",9 "AutoModel": "dangvantuan/bilingual_impl--modelling.BilingualModel",10 "AutoModelForMaskedLM": "dangvantuan/bilingual_impl--modelling.BilingualForMaskedLM",11 "AutoModelForMultipleChoice": "dangvantuan/bilingual_impl--modelling.BilingualForMultipleChoice",12 "AutoModelForQuestionAnswering": "dangvantuan/bilingual_impl--modelling.BilingualForQuestionAnswering",13 "AutoModelForSequenceClassification": "dangvantuan/bilingual_impl--modelling.BilingualForSequenceClassification",14 "AutoModelForTokenClassification": "dangvantuan/bilingual_impl--modelling.BilingualForTokenClassification"15 },16 "classifier_dropout": 0.0,17 "hidden_act": "gelu",18 "hidden_dropout_prob": 0.1,19 "hidden_size": 768,20 "id2label": {21 "0": "LABEL_0"22 },23 "initializer_range": 0.02,24 "intermediate_size": 3072,25 "label2id": {26 "LABEL_0": 027 },28 "layer_norm_eps": 1e-12,29 "layer_norm_type": "layer_norm",30 "logn_attention_clip1": false,31 "logn_attention_scale": false,32 "max_position_embeddings": 8192,33 "model_type": "Bilingual",34 "num_attention_heads": 12,35 "num_hidden_layers": 12,36 "pack_qkv": true,37 "pad_token_id": 1,38 "position_embedding_type": "rope",39 "rope_scaling": {40 "factor": 8.0,41 "type": "ntk"42 },43 "rope_theta": 20000,44 "torch_dtype": "float32",45 "transformers_version": "4.42.3",46 "type_vocab_size": 1,47 "unpad_inputs": false,48 "use_memory_efficient_attention": false,49 "vocab_size": 25004850}