{
  "_name_or_path": "susnato/clvp_dev",
  "architectures": [
    "ClvpModelForConditionalGeneration"
  ],
  "initializer_factor": 1.0,
  "logit_scale_init_value": 2.6592,
  "model_type": "clvp",
  "projection_dim": 768,
  "text_config": {
    "_name_or_path": "",
    "add_cross_attention": false,
    "architectures": null,
    "attention_dropout": 0.1,
    "bad_words_ids": null,
    "bos_token_id": 255,
    "chunk_size_feed_forward": 0,
    "cross_attention_hidden_size": null,
    "decoder_start_token_id": null,
    "diversity_penalty": 0.0,
    "do_sample": false,
    "dropout": 0.1,
    "early_stopping": false,
    "encoder_no_repeat_ngram_size": 0,
    "eos_token_id": 0,
    "finetuning_task": null,
    "forced_bos_token_id": null,
    "forced_eos_token_id": null,
    "hidden_act": "gelu",
    "hidden_size": 768,
    "initializer_factor": 1.0,
    "intermediate_size": 1536,
    "is_decoder": false,
    "is_encoder_decoder": false,
    "layer_norm_eps": 1e-05,
    "length_penalty": 1.0,
    "max_length": 20,
    "min_length": 0,
    "model_type": "clvp_encoder",
    "no_repeat_ngram_size": 0,
    "num_attention_heads": 12,
    "use_attention_bias": false,
    "num_beam_groups": 1,
    "num_beams": 1,
    "num_hidden_layers": 20,
    "num_return_sequences": 1,
    "output_attentions": false,
    "output_hidden_states": false,
    "output_scores": false,
    "pad_token_id": 0,
    "prefix": null,
    "projection_dim": 768,
    "problem_type": null,
    "pruned_heads": {},
    "remove_invalid_values": false,
    "repetition_penalty": 1.0,
    "return_dict": false,
    "return_dict_in_generate": false,
    "sep_token_id": null,
    "task_specific_params": null,
    "temperature": 1.0,
    "tie_encoder_decoder": false,
    "tie_word_embeddings": true,
    "tokenizer_class": null,
    "top_k": 50,
    "top_p": 1.0,
    "torch_dtype": null,
    "torchscript": false,
    "use_bfloat16": false,
    "vocab_size": 256,
    "ff_post_act_layer_norm": false,
    "use_rotary_embedding": true,
    "summary_type": "mean"
  },
  "speech_config": {
    "_name_or_path": "",
    "add_cross_attention": false,
    "architectures": null,
    "attention_dropout": 0.1,
    "bad_words_ids": null,
    "bos_token_id": 0,
    "chunk_size_feed_forward": 0,
    "cross_attention_hidden_size": null,
    "decoder_start_token_id": null,
    "diversity_penalty": 0.0,
    "do_sample": false,
    "dropout": 0.1,
    "early_stopping": false,
    "encoder_no_repeat_ngram_size": 0,
    "eos_token_id": 2,
    "finetuning_task": null,
    "forced_bos_token_id": null,
    "forced_eos_token_id": null,
    "hidden_act": "gelu",
    "hidden_size": 768,
    "vocab_size": 8192,
    "initializer_factor": 1.0,
    "intermediate_size": 1536,
    "is_decoder": false,
    "is_encoder_decoder": false,
    "layer_norm_eps": 1e-05,
    "length_penalty": 1.0,
    "max_length": 20,
    "min_length": 0,
    "model_type": "clvp_encoder",
    "no_repeat_ngram_size": 0,
    "num_attention_heads": 12,
    "num_beam_groups": 1,
    "num_beams": 1,
    "num_hidden_layers": 20,
    "use_attention_bias": false,
    "num_return_sequences": 1,
    "output_attentions": false,
    "output_hidden_states": false,
    "output_scores": false,
    "pad_token_id": 1,
    "patch_size": 32,
    "prefix": null,
    "projection_dim" : 768,
    "problem_type": null,
    "pruned_heads": {},
    "remove_invalid_values": false,
    "repetition_penalty": 1.0,
    "return_dict": true,
    "return_dict_in_generate": false,
    "sep_token_id": null,
    "task_specific_params": null,
    "temperature": 1.0,
    "tie_encoder_decoder": false,
    "tie_word_embeddings": true,
    "tokenizer_class": null,
    "top_k": 50,
    "top_p": 1.0,
    "torch_dtype": null,
    "torchscript": false,
    "use_bfloat16": false,
    "ff_post_act_layer_norm": false,
    "use_rotary_embedding": true,
    "summary_type": "mean"
  },
  "decoder_config": {
    "initializer_factor": 1.0,
    "activation_function": "gelu_new",
    "attention_dropout": 0.1,
    "bos_token_id": 8192,
    "embd_pdrop": 0.1,
    "eos_token_id": 8193,
    "initializer_range": 0.02,
    "layer_norm_epsilon": 1e-05,
    "model_type": "clvp_decoder",
    "n_ctx": 1012,
    "hidden_size": 1024,
    "num_attention_heads": 16,
    "num_hidden_layers": 30,
    "num_mel_attn_blocks": 6,
    "max_position_embeddings": 608,
    "max_text_tokens": 404,
    "resid_pdrop": 0.1,
    "summary_activation": null,
    "summary_first_dropout": 0.1,
    "summary_proj_to_labels": true,
    "use_attention_bias": true,
    "summary_type": "cls_index",
    "summary_use_proj": true,
    "vocab_size": 8194,
    "feature_size": 80,
    "decoder_fixing_codes": [83, 45, 45, 248]
  }
}