jupyterjazz's picture
Update config.json
1030c75 verified
{
"_name_or_path": "jina-embeddings-v3-xlm-large-pairs-vol3-temp-0.02-lora",
"architectures": [
"XLMRobertaLoRA"
],
"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_lora.XLMRobertaLoRA",
"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": 256,
"initializer_range": 0.02,
"intermediate_size": 1024,
"layer_norm_eps": 1e-05,
"load_trained_adapters": true,
"lora_adaptations": ["retrieval.query", "retrieval.passage", "separation", "classification", "text-matching"],
"lora_alpha": 1,
"lora_dropout_p": 0.0,
"lora_main_params_trainable": true,
"lora_rank": 4,
"matryoshka_dimensions": null,
"max_position_embeddings": 8194,
"num_attention_heads": 2,
"num_hidden_layers": 2,
"output_past": true,
"pad_token_id": 1,
"position_embedding_type": "rotary",
"torch_dtype": "float32",
"transformers_version": "4.30.2",
"truncate_dim": null,
"type_vocab_size": 1,
"use_cache": true,
"use_flash_attn": true,
"vocab_size": 250002,
"task_instructions": {
"retrieval.query": "Represent the query for retrieving evidence documents: ",
"retrieval.passage": "Represent the document for retrieval: ",
"separation": "",
"classification": "",
"text-matching": ""
}
}