config.json
| 1 | { |
| 2 | "_name_or_path": "jinaai/jina-reranker-v2-base-multilingual", |
| 3 | "architectures": ["XLMRobertaForSequenceClassification"], |
| 4 | "attention_probs_dropout_prob": 0.1, |
| 5 | "auto_map": { |
| 6 | "AutoConfig": "configuration_xlm_roberta.XLMRobertaFlashConfig", |
| 7 | "AutoModel": "modeling_xlm_roberta.XLMRobertaModel", |
| 8 | "AutoModelForSequenceClassification": "modeling_xlm_roberta.XLMRobertaForSequenceClassification" |
| 9 | }, |
| 10 | "bos_token_id": 0, |
| 11 | "classifier_dropout": null, |
| 12 | "emb_pooler": null, |
| 13 | "eos_token_id": 2, |
| 14 | "hidden_act": "gelu", |
| 15 | "hidden_dropout_prob": 0.1, |
| 16 | "hidden_size": 768, |
| 17 | "num_labels": 1, |
| 18 | "id2label": { |
| 19 | "0": "LABEL_0" |
| 20 | }, |
| 21 | "initializer_range": 0.02, |
| 22 | "intermediate_size": 3072, |
| 23 | "label2id": { |
| 24 | "LABEL_0": 0 |
| 25 | }, |
| 26 | "layer_norm_eps": 1e-5, |
| 27 | "max_position_embeddings": 1026, |
| 28 | "num_attention_heads": 12, |
| 29 | "num_hidden_layers": 12, |
| 30 | "output_past": true, |
| 31 | "pad_token_id": 1, |
| 32 | "position_embedding_type": "absolute", |
| 33 | "torch_dtype": "bfloat16", |
| 34 | "transformers_version": "4.40.0", |
| 35 | "type_vocab_size": 1, |
| 36 | "use_cache": false, |
| 37 | "use_flash_attn": true, |
| 38 | "vocab_size": 250002 |
| 39 | } |
| 40 | |