Unified_Audio_Schema / config.json
root
initial commit
8fb7827
{
"architectures": [
"UASAudioForCausalLM"
],
"audio_encoder_config": {
"activation_dropout": 0,
"activation_function": "gelu",
"attention_dropout": 0,
"conv_chunksize": 500,
"d_model": 1280,
"downsample_hidden_size": 480,
"dropout": 0,
"encoder_attention_heads": 20,
"encoder_ffn_dim": 5120,
"encoder_layers": 32,
"initializer_range": 0.02,
"max_source_positions": 1500,
"model_type": "uas_audio_encoder",
"n_window": 50,
"n_window_infer": 800,
"num_hidden_layers": 32,
"num_mel_bins": 128
},
"audio_token": 151646,
"auto_map": {
"AutoConfig": "configuration_uas_audio.UASAudioConfig",
"AutoModelForCausalLM": "modeling_uas_audio.UASAudioForCausalLM"
},
"dtype": "bfloat16",
"eos_token_id": 151645,
"model_type": "uas_audio",
"pad_token_id": 151643,
"text_config": {
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"hidden_act": "silu",
"hidden_size": 3584,
"initializer_range": 0.02,
"intermediate_size": 18944,
"layer_types": [
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention"
],
"max_position_embeddings": 16384,
"max_window_layers": 28,
"model_type": "qwen2",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000.0,
"sliding_window": null,
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 159864
},
"transformers_version": "4.57.3"
}