| { |
| "_name_or_path": "Tochka-AI/ruRoPEBert-e5-base-2k", |
| "architectures": [ |
| "BertForSequenceClassification" |
| ], |
| "attention_probs_dropout_prob": 0.1, |
| "auto_map": { |
| "AutoConfig": "Tochka-AI/ruRoPEBert-e5-base-2k--modeling_rope_bert.RoPEBertConfig", |
| "AutoModel": "Tochka-AI/ruRoPEBert-e5-base-2k--modeling_rope_bert.RoPEBertModel", |
| "AutoModelForMaskedLM": "Tochka-AI/ruRoPEBert-e5-base-2k--modeling_rope_bert.RoPEBertForMaskedLM", |
| "AutoModelForSequenceClassification": "Tochka-AI/ruRoPEBert-e5-base-2k--modeling_rope_bert.RoPEBertForSequenceClassification" |
| }, |
| "classifier_dropout": null, |
| "hidden_act": "gelu", |
| "hidden_dropout_prob": 0.1, |
| "hidden_size": 768, |
| "initializer_range": 0.02, |
| "intermediate_size": 3072, |
| "layer_norm_eps": 1e-12, |
| "max_position_embeddings": 2048, |
| "model_type": "bert", |
| "num_attention_heads": 12, |
| "num_hidden_layers": 12, |
| "pad_token_id": 1, |
| "pooler_type": "mean", |
| "position_embedding_type": "absolute", |
| "problem_type": "single_label_classification", |
| "rope_scaling": null, |
| "rope_theta": 10000.0, |
| "torch_dtype": "float32", |
| "transformers_version": "4.45.1", |
| "type_vocab_size": 1, |
| "use_cache": true, |
| "vocab_size": 69382 |
| } |
|
|
