{
  "architectures": [
    "IndicCanaryForConditionalGeneration"
  ],
  "auto_map": {
    "AutoConfig": "configuration_indic_canary.IndicCanaryConfig",
    "AutoModel": "modeling_indic_canary.IndicCanaryForConditionalGeneration",
    "AutoModelForSpeechSeq2Seq": "modeling_indic_canary.IndicCanaryForConditionalGeneration"
  },
  "bos_token_id": 4,
  "conv_kernel_size": 9,
  "d_model": 1024,
  "decoder_attention_heads": 8,
  "decoder_ffn_dim": 4096,
  "decoder_layers": 24,
  "decoder_start_token_id": 7,
  "dtype": "float32",
  "encoder_attention_heads": 8,
  "encoder_ffn_dim": 4096,
  "encoder_layers": 32,
  "eos_token_id": 3,
  "is_encoder_decoder": true,
  "max_generation_delta": 50,
  "max_target_positions": 1024,
  "model_type": "indic_canary",
  "num_mel_bins": 128,
  "pad_token_id": 2,
  "quantization_config": {
    "_load_in_4bit": false,
    "_load_in_8bit": true,
    "bnb_4bit_compute_dtype": "float32",
    "bnb_4bit_quant_storage": "uint8",
    "bnb_4bit_quant_type": "fp4",
    "bnb_4bit_use_double_quant": false,
    "llm_int8_enable_fp32_cpu_offload": false,
    "llm_int8_has_fp16_weight": false,
    "llm_int8_skip_modules": [
      "model.encoder.pre_encode.out",
      "lm_head"
    ],
    "llm_int8_threshold": 6.0,
    "load_in_4bit": false,
    "load_in_8bit": true,
    "quant_method": "bitsandbytes"
  },
  "subsampling_conv_channels": 256,
  "subsampling_factor": 8,
  "tie_word_embeddings": true,
  "transformers_version": "5.12.1",
  "vocab_size": 7152
}