| { | |
| "_name_or_path": "aari1995/gbert-large-nli_mix", | |
| "architectures": [ | |
| "JinaBertModel" | |
| ], | |
| "attention_probs_dropout_prob": 0.0, | |
| "attn_implementation": null, | |
| "auto_map": { | |
| "AutoConfig": "aari1995/gbert-large-alibi--configuration_bert.JinaBertConfig", | |
| "AutoModel": "aari1995/gbert-large-alibi--modeling_bert.JinaBertModel", | |
| "AutoModelForMaskedLM": "aari1995/gbert-large-alibi--modeling_bert.JinaBertForMaskedLM", | |
| "AutoModelForSequenceClassification": "aari1995/gbert-large-alibi--modeling_bert.JinaBertForSequenceClassification" | |
| }, | |
| "classifier_dropout": null, | |
| "emb_pooler": null, | |
| "feed_forward_type": "original", | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 1024, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 4096, | |
| "layer_norm_eps": 1e-12, | |
| "max_position_embeddings": 8192, | |
| "model_type": "bert", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 24, | |
| "pad_token_id": 0, | |
| "position_embedding_type": "alibi", | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.42.0.dev0", | |
| "type_vocab_size": 2, | |
| "use_cache": true, | |
| "vocab_size": 31102 | |
| } | |