| { |
| "architectures": [ |
| "XLMRobertaModel" |
| ], |
| "attention_probs_dropout_prob": 0.1, |
| "auto_map": { |
| "AutoConfig": "jinaai/xlm-roberta-flash-implementation--configuration_xlm_roberta.XLMRobertaFlashConfig", |
| "AutoModel": "jinaai/xlm-roberta-flash-implementation--modeling_xlm_roberta.XLMRobertaModel", |
| "AutoModelForMaskedLM": "jinaai/xlm-roberta-flash-implementation--modeling_xlm_roberta.XLMRobertaForMaskedLM", |
| "AutoModelForPreTraining": "jinaai/xlm-roberta-flash-implementation--modeling_xlm_roberta.XLMRobertaForPreTraining" |
| }, |
| "bos_token_id": 0, |
| "classifier_dropout": null, |
| "emb_pooler": null, |
| "eos_token_id": 2, |
| "hidden_act": "gelu", |
| "hidden_dropout_prob": 0.1, |
| "hidden_size": 1024, |
| "initializer_range": 0.02, |
| "intermediate_size": 4096, |
| "layer_norm_eps": 1e-05, |
| "load_trained_adapters": false, |
| "lora_adaptations": null, |
| "lora_alpha": 1, |
| "lora_dropout_p": 0.0, |
| "lora_main_params_trainable": false, |
| "lora_prompts": null, |
| "lora_rank": 4, |
| "matryoshka_dimensions": null, |
| "max_position_embeddings": 8194, |
| "model_type": "xlm-roberta", |
| "num_attention_heads": 16, |
| "num_hidden_layers": 24, |
| "output_past": true, |
| "pad_token_id": 1, |
| "position_embedding_type": "rotary", |
| "rotary_emb_base": 10000.0, |
| "task_instructions": null, |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.51.3", |
| "truncate_dim": null, |
| "type_vocab_size": 1, |
| "use_cache": true, |
| "use_flash_attn": true, |
| "use_reentrant": false, |
| "vocab_size": 250004 |
| } |
|
|