config.json

{
  "_commit_hash": null,
  "all_docs": [
    [
      [
        1,
        283,
        24599,
        36305,
        2
      ],
      [
        1,
        67272,
        5374,
        2,
        0
      ],
      [
        1,
        12778,
        8102,
        2,
        0
      ],
      [
        1,
        55436,
        13128,
        547,
        2
      ],
      [
        1,
        961,
        2837,
        2,
        0
      ],
      [
        1,
        4175,
        2,
        0,
        0
      ]
    ],
    [
      [
        1,
        1,
        1,
        1,
        1
      ],
      [
        1,
        1,
        1,
        1,
        0
      ],
      [
        1,
        1,
        1,
        1,
        0
      ],
      [
        1,
        1,
        1,
        1,
        1
      ],
      [
        1,
        1,
        1,
        1,
        0
      ],
      [
        1,
        1,
        1,
        0,
        0
      ]
    ]
  ],
  "architectures": [
    "FastFitTrainable"
  ],
  "clf_dim": 6,
  "clf_doc": false,
  "clf_factor": 0.1,
  "clf_level": "cls",
  "clf_loss_factor": 0.1,
  "clf_query": true,
  "encoder": {
    "_name_or_path": "microsoft/deberta-v3-xsmall",
    "add_cross_attention": false,
    "architectures": null,
    "attention_probs_dropout_prob": 0.1,
    "bad_words_ids": null,
    "begin_suppress_tokens": null,
    "bos_token_id": null,
    "chunk_size_feed_forward": 0,
    "cross_attention_hidden_size": null,
    "decoder_start_token_id": null,
    "diversity_penalty": 0.0,
    "do_sample": false,
    "early_stopping": false,
    "encoder_no_repeat_ngram_size": 0,
    "eos_token_id": null,
    "exponential_decay_length_penalty": null,
    "finetuning_task": null,
    "forced_bos_token_id": null,
    "forced_eos_token_id": null,
    "hidden_act": "gelu",
    "hidden_dropout_prob": 0.1,
    "hidden_size": 384,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "initializer_range": 0.02,
    "intermediate_size": 1536,
    "is_decoder": false,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "layer_norm_eps": 1e-07,
    "length_penalty": 1.0,
    "max_length": 20,
    "max_position_embeddings": 512,
    "max_relative_positions": -1,
    "min_length": 0,
    "model_type": "deberta-v2",
    "no_repeat_ngram_size": 0,
    "norm_rel_ebd": "layer_norm",
    "num_attention_heads": 6,
    "num_beam_groups": 1,
    "num_beams": 1,
    "num_hidden_layers": 12,
    "num_return_sequences": 1,
    "output_attentions": false,
    "output_hidden_states": false,
    "output_scores": false,
    "pad_token_id": 0,
    "pooler_dropout": 0,
    "pooler_hidden_act": "gelu",
    "pooler_hidden_size": 384,
    "pos_att_type": [
      "p2c",
      "c2p"
    ],
    "position_biased_input": false,
    "position_buckets": 256,
    "prefix": null,
    "problem_type": null,
    "pruned_heads": {},
    "relative_attention": true,
    "remove_invalid_values": false,
    "repetition_penalty": 1.0,
    "return_dict": true,
    "return_dict_in_generate": false,
    "sep_token_id": null,
    "share_att_key": true,
    "suppress_tokens": null,
    "task_specific_params": null,
    "temperature": 1.0,
    "tf_legacy_loss": false,
    "tie_encoder_decoder": false,
    "tie_word_embeddings": true,
    "tokenizer_class": null,
    "top_k": 50,
    "top_p": 1.0,
    "torch_dtype": null,
    "torchscript": false,
    "transformers_version": "4.40.1",
    "type_vocab_size": 0,
    "typical_p": 1.0,
    "use_bfloat16": false,
    "vocab_size": 128100
  },
  "encoder_dropout": null,
  "encoding_type": "dual",
  "hidden_size": 384,
  "id2label": {
    "0": "ashirwad",
    "1": "asia_hip",
    "2": "hoang",
    "3": "mundfein",
    "4": "rewe",
    "5": "unknown"
  },
  "inference_direction": "doc",
  "inference_type": "sim",
  "init_freeze": "all",
  "label2id": {
    "ashirwad": 0,
    "asia_hip": 1,
    "hoang": 2,
    "mundfein": 3,
    "rewe": 4,
    "unknown": 5
  },
  "length_norm": true,
  "mask_prob": 0.0,
  "mask_zeros_in_doc": false,
  "mask_zeros_in_query": false,
  "mlm_factor": 0.0,
  "mlm_prob": 0.0,
  "model_type": "FastFit",
  "num_repeats": 4,
  "pretrain_mode": false,
  "proj_dim": 128,
  "rep_tokens": "all",
  "scores_temp": 0.07,
  "sim_factor": 1.0,
  "similarity_metric": "cosine",
  "symetric_mode": true,
  "torch_dtype": "float32",
  "transformers_version": null
}