config.json

{
  "architectures": [
    "MoshiForConditionalGeneration"
  ],
  "attention_dropout": 0.0,
  "audio_encoder": {
    "_name_or_path": "kyutai/mimi",
    "add_cross_attention": false,
    "architectures": [
      "MimiModel"
    ],
    "attention_bias": false,
    "attention_dropout": 0.0,
    "audio_channels": 1,
    "bad_words_ids": null,
    "begin_suppress_tokens": null,
    "bos_token_id": null,
    "chunk_size_feed_forward": 0,
    "codebook_dim": 256,
    "codebook_size": 2048,
    "compress": 2,
    "cross_attention_hidden_size": null,
    "decoder_start_token_id": null,
    "dilation_growth_rate": 2,
    "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,
    "frame_rate": 12.5,
    "head_dim": 64,
    "hidden_act": "gelu",
    "hidden_size": 512,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "initializer_range": 0.02,
    "intermediate_size": 2048,
    "is_decoder": false,
    "is_encoder_decoder": false,
    "kernel_size": 7,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "last_kernel_size": 3,
    "layer_scale_initial_scale": 0.01,
    "length_penalty": 1.0,
    "max_length": 20,
    "max_position_embeddings": 8000,
    "min_length": 0,
    "model_type": "mimi",
    "no_repeat_ngram_size": 0,
    "norm_eps": 1e-05,
    "normalize": false,
    "num_attention_heads": 8,
    "num_beam_groups": 1,
    "num_beams": 1,
    "num_filters": 64,
    "num_hidden_layers": 8,
    "num_key_value_heads": 8,
    "num_quantizers": 32,
    "num_residual_layers": 1,
    "num_return_sequences": 1,
    "num_semantic_quantizers": 1,
    "output_attentions": false,
    "output_hidden_states": false,
    "output_scores": false,
    "pad_mode": "constant",
    "pad_token_id": null,
    "prefix": null,
    "problem_type": null,
    "pruned_heads": {},
    "remove_invalid_values": false,
    "repetition_penalty": 1.0,
    "residual_kernel_size": 3,
    "return_dict": true,
    "return_dict_in_generate": false,
    "rope_theta": 10000.0,
    "sampling_rate": 24000,
    "sep_token_id": null,
    "sliding_window": 250,
    "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,
    "trim_right_ratio": 1.0,
    "typical_p": 1.0,
    "upsample_groups": 512,
    "upsampling_ratios": [
      8,
      6,
      5,
      4
    ],
    "use_bfloat16": false,
    "use_cache": false,
    "use_causal_conv": true,
    "use_conv_shortcut": false,
    "vector_quantization_hidden_dimension": 256
  },
  "audio_vocab_size": 2048,
  "depth_ffn_dim": 5632,
  "depth_head_dim": 64,
  "depth_hidden_size": 1024,
  "depth_max_position_embeddings": 9,
  "depth_num_attention_heads": 16,
  "depth_num_hidden_layers": 6,
  "depth_num_key_value_heads": 16,
  "depth_sliding_window": 8,
  "ffn_dim": 22528,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "max_position_embeddings": 3000,
  "model_type": "moshi",
  "num_attention_heads": 32,
  "num_codebooks": 8,
  "num_hidden_layers": 32,
  "num_key_value_heads": 32,
  "rms_norm_eps": 1e-08,
  "rope_theta": 10000.0,
  "sliding_window": 3000,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.46.0.dev0",
  "use_cache": true,
  "vocab_size": 32000
}