latest-eot / config.json
NMCxyz's picture
Upload folder
f6cefef verified
{
"_name_or_path": "/data1/speech/anhnmt2/cuongnm/EOT/Qwen2.5-0.5B-Instruct",
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"eot_loss_weight": 1.0,
"hidden_act": "silu",
"hidden_size": 896,
"initializer_range": 0.02,
"intermediate_size": 4864,
"max_position_embeddings": 32768,
"max_window_layers": 21,
"model_type": "asr_speech_qwen2",
"num_attention_heads": 14,
"num_hidden_layers": 24,
"num_key_value_heads": 2,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000.0,
"sliding_window": null,
"speech_encoder": "/data1/speech/anhnmt2/Speech2Speech/LLaMA-Omni/models/speech_encoder/whisper-medium",
"speech_encoder_ds_rate": 5,
"speech_encoder_hidden_size": 1024,
"speech_encoder_type": "whisper",
"speech_normalize": false,
"speech_projector_lr": null,
"speech_projector_type": "linear",
"tie_word_embeddings": true,
"tokenizer_model_max_length": 1024,
"tokenizer_padding_side": "right",
"torch_dtype": "bfloat16",
"transformers_version": "4.45.0",
"tune_speech_projector": true,
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 151665
}