{
  "architectures": [
    "ZeroShotClassifierHF"
  ],
  "device": "cuda",
  "embedder_config": {
    "_attn_implementation_autoset": false,
    "_name_or_path": "deepvk/USER2-base",
    "activation_function": "gelu",
    "add_cross_attention": false,
    "allow_embedding_resizing": true,
    "architectures": [
      "ModernBertModel"
    ],
    "attention_bias": false,
    "attention_dropout": 0.0,
    "attention_layer": "rope",
    "attention_probs_dropout_prob": 0.0,
    "attn_out_bias": false,
    "attn_out_dropout_prob": 0.1,
    "attn_qkv_bias": false,
    "bad_words_ids": null,
    "begin_suppress_tokens": null,
    "bert_layer": "prenorm",
    "bos_token_id": 50281,
    "chunk_size_feed_forward": 0,
    "classifier_activation": "gelu",
    "classifier_bias": false,
    "classifier_dropout": 0.0,
    "classifier_pooling": "cls",
    "cls_token_id": 50281,
    "compile_model": true,
    "cross_attention_hidden_size": null,
    "decoder_bias": true,
    "decoder_start_token_id": null,
    "deterministic_flash_attn": false,
    "diversity_penalty": 0.0,
    "do_sample": false,
    "early_stopping": false,
    "embed_dropout_prob": 0.0,
    "embed_norm": true,
    "embedding_dropout": 0.0,
    "embedding_layer": "sans_pos",
    "encoder_no_repeat_ngram_size": 0,
    "eos_token_id": 50282,
    "exponential_decay_length_penalty": null,
    "final_norm": true,
    "finetuning_task": null,
    "forced_bos_token_id": null,
    "forced_eos_token_id": null,
    "global_attn_every_n_layers": 3,
    "global_rope_theta": 160000.0,
    "head_pred_act": "gelu",
    "hidden_act": "gelu",
    "hidden_activation": "gelu",
    "hidden_dropout_prob": 0.0,
    "hidden_size": 768,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "init_method": "full_megatron",
    "initializer_cutoff_factor": 2.0,
    "initializer_range": 0.02,
    "intermediate_size": 1152,
    "is_decoder": false,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "layer_norm_eps": 1e-05,
    "length_penalty": 1.0,
    "local_attention": 128,
    "local_attn_rotary_emb_base": 10000.0,
    "local_rope_theta": 10000.0,
    "loss_function": "fa_cross_entropy",
    "loss_kwargs": {
      "reduction": "mean"
    },
    "masked_prediction": true,
    "max_length": 20,
    "max_position_embeddings": 8192,
    "min_length": 0,
    "mlp_bias": false,
    "mlp_dropout": 0.0,
    "mlp_dropout_prob": 0.0,
    "mlp_in_bias": false,
    "mlp_layer": "glu",
    "mlp_out_bias": false,
    "model_type": "modernbert",
    "no_repeat_ngram_size": 0,
    "norm_bias": false,
    "norm_eps": 1e-05,
    "norm_kwargs": {
      "bias": false,
      "eps": 1e-05
    },
    "normalization": "layernorm",
    "num_attention_heads": 12,
    "num_beam_groups": 1,
    "num_beams": 1,
    "num_hidden_layers": 22,
    "num_return_sequences": 1,
    "output_attentions": false,
    "output_hidden_states": false,
    "output_scores": false,
    "pad_token_id": 50283,
    "padding": "unpadded",
    "prefix": null,
    "problem_type": null,
    "pruned_heads": {},
    "reference_compile": null,
    "remove_invalid_values": false,
    "repad_logits_with_grad": false,
    "repetition_penalty": 1.0,
    "return_dict": true,
    "return_dict_in_generate": false,
    "rotary_emb_base": 160000.0,
    "rotary_emb_dim": null,
    "rotary_emb_interleaved": false,
    "rotary_emb_scale_base": null,
    "sep_token_id": 50282,
    "skip_first_prenorm": true,
    "sliding_window": 128,
    "sparse_pred_ignore_index": -100,
    "sparse_prediction": false,
    "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": "float32",
    "torchscript": false,
    "typical_p": 1.0,
    "unpad_embeddings": true,
    "use_bfloat16": false,
    "vocab_size": 50370
  },
  "embedder_name": "deepvk/USER2-base",
  "ffn_classes_dropout": 0.4,
  "ffn_dim": 2048,
  "ffn_text_dropout": 0.4,
  "hidden_size": 768,
  "loss_args": {
    "loss_type": "bce"
  },
  "model_type": "GeRaCl",
  "pooling_type": "mean",
  "tokenizer_len": 50370,
  "torch_dtype": "float32",
  "transformers_version": "4.48.2"
}