{ "_name_or_path": "LLaMA-Omni2-7B", "architectures": [ "Omni2Speech2SQwen2ForCausalLM" ], "attention_dropout": 0.0, "bos_token_id": 151643, "eos_token_id": 151645, "hidden_act": "silu", "hidden_size": 3584, "initializer_range": 0.02, "intermediate_size": 18944, "max_position_embeddings": 32768, "max_window_layers": 28, "model_type": "omni2_speech2s_qwen2", "num_attention_heads": 28, "num_hidden_layers": 28, "num_key_value_heads": 4, "rms_norm_eps": 1e-06, "rope_theta": 1000000.0, "sliding_window": null, "speech_encoder": "models/speech_encoder/large-v3.pt", "speech_encoder_ds_rate": 5, "speech_encoder_hidden_size": 1280, "speech_encoder_type": "whisper", "speech_generator": { "architectures": [ "Qwen2ForCausalLM" ], "attention_dropout": 0.0, "bos_token_id": 151643, "eos_token_id": 151643, "hidden_act": "silu", "hidden_size": 896, "initializer_range": 0.02, "intermediate_size": 4864, "max_position_embeddings": 32768, "max_window_layers": 24, "model_type": "qwen2", "num_attention_heads": 14, "num_hidden_layers": 24, "num_key_value_heads": 2, "rms_norm_eps": 1e-06, "rope_theta": 1000000.0, "sliding_window": null, "tie_word_embeddings": true, "torch_dtype": "bfloat16", "transformers_version": "4.43.4", "use_cache": true, "use_mrope": false, "use_sliding_window": false, "vocab_size": 158227 }, "speech_projector_type": "linear", "stream_params": "(3,10)", "tie_word_embeddings": false, "tokenizer_model_max_length": 4096, "tokenizer_padding_side": "right", "torch_dtype": "bfloat16", "transformers_version": "4.43.4", "unit_vocab_size": 6561, "use_cache": true, "use_sliding_window": false, "vocab_size": 152064 }