{
  "_name_or_path": "/linzhihang/zhangyuhao/ACLlama_s2s/output/S2S/S2S_finetune_small_lr1e-4_S2S-KD-unit-languge-new-0804-filter_kd_offline_base_merge_0808_20string_1e-4/checkpoint-16000",
  "adapter_size": 1280,
  "architectures": [
    "ACLlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "audio_token_len": 750,
  "audio_tower": "/linzhihang/LLMs/whisper-v3",
  "bos_token_id": 128000,
  "eos_token_id": [
    128001,
    128008,
    128009
  ],
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 14336,
  "max_position_embeddings": 131072,
  "mlp_bias": false,
  "model_type": "ACLlama",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 8,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": {
    "factor": 8.0,
    "high_freq_factor": 4.0,
    "low_freq_factor": 1.0,
    "original_max_position_embeddings": 8192,
    "rope_type": "llama3"
  },
  "rope_theta": 500000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.48.1",
  "unit_output": "finetune_kd",
  "unit_vocab": "/linzhihang/zhangyuhao/unit_language/v6.8k.dict",
  "unit_vocab_size": 7807,
  "use_cache": false,
  "vocab_size": 128257
}