config.json

{
  "vocab_size": 277404,
  "max_position_embeddings": 8192,
  "hidden_size": 2048,
  "logit_scale": 1.0,
  "intermediate_size": 11008,
  "num_hidden_layers": 36,
  "num_attention_heads": 16,
  "num_key_value_heads": 4,
  "hidden_act": "silu",
  "initializer_range": 0.02,
  "layer_norm_eps": 1e-05,
  "use_cache": true,
  "rope_theta": 50000,
  "rope_scaling": null,
  "attention_bias": false,
  "attention_dropout": 0.0,
  "sliding_window": 4096,
  "layer_types": [
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention"
  ],
  "head_dim": 128,
  "return_dict": true,
  "output_hidden_states": false,
  "torchscript": false,
  "dtype": "bfloat16",
  "pruned_heads": {},
  "tie_word_embeddings": true,
  "chunk_size_feed_forward": 0,
  "is_encoder_decoder": false,
  "is_decoder": false,
  "cross_attention_hidden_size": null,
  "add_cross_attention": false,
  "tie_encoder_decoder": false,
  "architectures": [
    "TinyAyaForCausalLM"
  ],
  "finetuning_task": null,
  "id2label": {
    "0": "LABEL_0",
    "1": "LABEL_1"
  },
  "label2id": {
    "LABEL_0": 0,
    "LABEL_1": 1
  },
  "task_specific_params": null,
  "problem_type": null,
  "tokenizer_class": null,
  "prefix": null,
  "bos_token_id": 2,
  "pad_token_id": 0,
  "eos_token_id": 3,
  "sep_token_id": null,
  "decoder_start_token_id": null,
  "max_length": 20,
  "min_length": 0,
  "do_sample": false,
  "early_stopping": false,
  "num_beams": 1,
  "temperature": 1.0,
  "top_k": 50,
  "top_p": 1.0,
  "typical_p": 1.0,
  "repetition_penalty": 1.0,
  "length_penalty": 1.0,
  "no_repeat_ngram_size": 0,
  "encoder_no_repeat_ngram_size": 0,
  "bad_words_ids": null,
  "num_return_sequences": 1,
  "output_scores": false,
  "return_dict_in_generate": false,
  "forced_bos_token_id": null,
  "forced_eos_token_id": null,
  "remove_invalid_values": false,
  "exponential_decay_length_penalty": null,
  "suppress_tokens": null,
  "begin_suppress_tokens": null,
  "num_beam_groups": 1,
  "diversity_penalty": 0.0,
  "_sliding_window_pattern": 4,
  "cache_implementation": "hybrid",
  "layer_switch": 4,
  "model_type": "tinyaya_mimi",
  "order_of_interleaved_layers": "local_attn_first",
  "position_embedding_type": "rope_gptj",
  "rotary_pct": 1.0,
  "sliding_window_pattern": 4,
  "use_embedding_sharing": true,
  "use_gated_activation": true,
  "use_parallel_block": true,
  "use_parallel_embedding": false,
  "use_qk_norm": false,
  "tf_legacy_loss": false,
  "use_bfloat16": false,
  "output_attentions": false,
  "num_quantizers": 8,
  "codebook_size": 2048,
  "audio_start_token_id": 277393,
  "audio_end_token_id": 277394,
  "speakers": [
    "Ira",
    "Aisha",
    "Siya",
    "Zoya",
    "Silver"
  ],
  "auto_map": {
    "AutoConfig": "configuration_tinyaya.TinyAyaConfig",
    "AutoModelForCausalLM": "modeling_tinyaya.TinyAyaForCausalLM"
  },
  "torch_dtype": "bfloat16"
}