Automatic Speech Recognition
Transformers
Safetensors
meralion3
meralion
meralion-3
custom_code
m_test_9 / config.json
lewiswoncy's picture
Upload MERaLiON3ForConditionalGeneration
2addc83 verified
{
"architectures": [
"MERaLiON3ForConditionalGeneration"
],
"auto_map": {
"AutoConfig": "configuration_meralion3.MERaLiON3Config",
"AutoModelForSpeechSeq2Seq": "modeling_meralion3.MERaLiON3ForConditionalGeneration",
"AutoProcessor": "processing_meralion3.MERaLiON3Processor"
},
"cache_implementation": "hybrid",
"dtype": "bfloat16",
"fixed_speech_embeds_length": 300,
"head_dim": 256,
"hidden_size": 3584,
"intermediate_size": 14336,
"model_type": "meralion3",
"num_attention_heads": 16,
"num_hidden_layers": 42,
"num_key_value_heads": 8,
"sliding_window": 4096,
"speech_config": {
"_name_or_path": "/data/projects/13003558/lewiswon/models/meralion_whisper_v3_normed_cleaned",
"activation_dropout": 0.0,
"activation_function": "gelu",
"apply_spec_augment": true,
"architectures": [
"WhisperForConditionalGeneration"
],
"attention_dropout": 0.0,
"begin_suppress_tokens": null,
"bos_token_id": 50257,
"classifier_proj_size": 256,
"d_model": 1280,
"decoder_attention_heads": 20,
"decoder_ffn_dim": 5120,
"decoder_layerdrop": 0.0,
"decoder_layers": 32,
"decoder_start_token_id": 50258,
"dropout": 0.0,
"dtype": "bfloat16",
"encoder_attention_heads": 20,
"encoder_ffn_dim": 5120,
"encoder_layerdrop": 0.0,
"encoder_layers": 32,
"eos_token_id": 50257,
"init_std": 0.02,
"mask_feature_length": 10,
"mask_feature_min_masks": 0,
"mask_feature_prob": 0.1,
"mask_time_length": 20,
"mask_time_min_masks": 2,
"mask_time_prob": 0.1,
"max_length": null,
"max_source_positions": 1500,
"max_target_positions": 448,
"median_filter_width": 7,
"model_type": "whisper",
"num_hidden_layers": 32,
"num_mel_bins": 128,
"scale_embedding": false,
"use_cache": true,
"use_weighted_layer_sum": true,
"vocab_size": 51866
},
"speech_mlp_scale_factor": 5,
"speech_mlp_use_projection": false,
"speech_token_index": 255999,
"text_config": {
"_name_or_path": "/home/models/gemma2_9b-sg-inst",
"architectures": [
"Gemma2ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"attn_logit_softcapping": 50.0,
"cache_implementation": "hybrid",
"dtype": "bfloat16",
"eos_token_id": 107,
"final_logit_softcapping": 30.0,
"head_dim": 256,
"hidden_act": "gelu_pytorch_tanh",
"hidden_activation": "gelu_pytorch_tanh",
"hidden_size": 3584,
"initializer_range": 0.02,
"intermediate_size": 14336,
"layer_types": [
"sliding_attention",
"full_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"full_attention"
],
"max_position_embeddings": 8192,
"model_type": "gemma2",
"num_attention_heads": 16,
"num_hidden_layers": 42,
"num_key_value_heads": 8,
"query_pre_attn_scalar": 256,
"rms_norm_eps": 1e-06,
"rope_theta": 10000.0,
"sliding_window": 4096,
"sliding_window_size": 4096,
"use_cache": true,
"vocab_size": 256000
},
"transformers_version": "4.56.2"
}