config.json

{
  "_commit_hash": "8fb12aedb4f83fd92be8337daa1dfabc0d70651c",
  "_name_or_path": "hf-internal-testing/tiny-clap-htsat-unfused",
  "architectures": [
    "ClapModel"
  ],
  "audio_config": {
    "_name_or_path": "",
    "add_cross_attention": false,
    "aff_block_r": 2,
    "architectures": null,
    "attention_dropout": 0.1,
    "attention_probs_dropout_prob": 0.0,
    "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,
    "depths": [
      2,
      2
    ],
    "diversity_penalty": 0.0,
    "do_sample": false,
    "drop_path_rate": 0.0,
    "dropout": 0.1,
    "early_stopping": false,
    "enable_fusion": false,
    "enable_patch_layer_norm": true,
    "encoder_no_repeat_ngram_size": 0,
    "eos_token_id": null,
    "exponential_decay_length_penalty": null,
    "finetuning_task": null,
    "flatten_patch_embeds": true,
    "forced_bos_token_id": null,
    "forced_eos_token_id": null,
    "freq_ratio": 2,
    "fusion_type": null,
    "hidden_act": "gelu",
    "hidden_dropout_prob": 0.1,
    "hidden_size": 64,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "image_size": 60,
    "initializer_factor": 1.0,
    "initializer_range": 0.02,
    "intermediate_size": 37,
    "is_decoder": false,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "layer_norm_eps": 1e-05,
    "length_penalty": 1.0,
    "max_length": 20,
    "min_length": 0,
    "mlp_ratio": 4.0,
    "model_type": "clap_audio_model",
    "no_repeat_ngram_size": 0,
    "num_attention_heads": [
      2,
      2,
      2,
      2
    ],
    "num_beam_groups": 1,
    "num_beams": 1,
    "num_channels": 3,
    "num_classes": 527,
    "num_hidden_layers": 3,
    "num_mel_bins": 64,
    "num_return_sequences": 1,
    "output_attentions": false,
    "output_hidden_states": false,
    "output_scores": false,
    "pad_token_id": null,
    "patch_embed_input_channels": 1,
    "patch_embeds_hidden_size": 32,
    "patch_size": 2,
    "patch_stride": 2,
    "prefix": null,
    "problem_type": null,
    "projection_dim": 32,
    "projection_hidden_act": "relu",
    "pruned_heads": {},
    "qkv_bias": true,
    "remove_invalid_values": false,
    "repetition_penalty": 1.0,
    "return_dict": true,
    "return_dict_in_generate": false,
    "sep_token_id": null,
    "spec_size": 256,
    "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": "4.27.0.dev0",
    "typical_p": 1.0,
    "use_bfloat16": false,
    "window_size": 4
  },
  "hidden_size": 32,
  "initializer_factor": 1.0,
  "logit_scale_init_value": 14.285714285714285,
  "model_type": "clap",
  "num_hidden_layers": 5,
  "projection_dim": 32,
  "projection_hidden_act": "relu",
  "text_config": {
    "_name_or_path": "",
    "add_cross_attention": false,
    "architectures": null,
    "attention_dropout": 0.1,
    "attention_probs_dropout_prob": 0.1,
    "bad_words_ids": null,
    "begin_suppress_tokens": null,
    "bos_token_id": 0,
    "chunk_size_feed_forward": 0,
    "classifier_dropout": null,
    "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,
    "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": 32,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "initializer_factor": 1.0,
    "initializer_range": 0.02,
    "intermediate_size": 37,
    "is_decoder": false,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "layer_norm_eps": 1e-12,
    "length_penalty": 1.0,
    "max_length": 20,
    "max_position_embeddings": 512,
    "min_length": 0,
    "model_type": "clap_text_model",
    "no_repeat_ngram_size": 0,
    "num_attention_heads": 2,
    "num_beam_groups": 1,
    "num_beams": 1,
    "num_hidden_layers": 3,
    "num_return_sequences": 1,
    "output_attentions": false,
    "output_hidden_states": false,
    "output_scores": false,
    "pad_token_id": 1,
    "position_embedding_type": "absolute",
    "prefix": null,
    "problem_type": null,
    "projection_dim": 32,
    "projection_hidden_act": "relu",
    "pruned_heads": {},
    "remove_invalid_values": false,
    "repetition_penalty": 1.0,
    "return_dict": true,
    "return_dict_in_generate": false,
    "sep_token_id": null,
    "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": "4.27.0.dev0",
    "type_vocab_size": 1,
    "typical_p": 1.0,
    "use_bfloat16": false,
    "use_cache": true,
    "vocab_size": 50265
  },
  "torch_dtype": "float32",
  "transformers_version": null
}