config.json

{
  "architectures": [
    "GlmAsrForConditionalGeneration"
  ],
  "audio_config": {
    "attention_dropout": 0.0,
    "head_dim": 64,
    "hidden_act": "gelu",
    "hidden_size": 1280,
    "initializer_range": 0.02,
    "intermediate_size": 5120,
    "max_position_embeddings": 1500,
    "model_type": "glmasr_encoder",
    "num_attention_heads": 20,
    "num_hidden_layers": 32,
    "num_key_value_heads": 20,
    "num_mel_bins": 128,
    "partial_rotary_factor": 0.5,
    "rope_parameters": {
      "partial_rotary_factor": 0.5,
      "rope_theta": 10000.0,
      "rope_type": "default"
    }
  },
  "audio_token_id": 59260,
  "dtype": "bfloat16",
  "hidden_size": 2048,
  "model_type": "glmasr",
  "projector_hidden_act": "gelu",
  "text_config": {
    "attention_bias": false,
    "attention_dropout": 0.0,
    "eos_token_id": [
      59246,
      59253,
      59255
    ],
    "head_dim": 128,
    "hidden_act": "silu",
    "hidden_size": 2048,
    "initializer_range": 0.02,
    "intermediate_size": 6144,
    "max_position_embeddings": 8192,
    "mlp_bias": false,
    "model_type": "llama",
    "num_attention_heads": 16,
    "num_hidden_layers": 28,
    "num_key_value_heads": 4,
    "pretraining_tp": 1,
    "rms_norm_eps": 1e-05,
    "rope_parameters": {
      "rope_theta": 10000.0,
      "rope_type": "default"
    },
    "use_cache": true,
    "vocab_size": 59264
  },
  "transformers_version": "5.0.0.dev0",
  "vocab_size": 59264
}