| { |
| "_name_or_path": "./Soundwave", |
| "adapter_size": 1280, |
| "architectures": [ |
| "SoundwaveForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "audio_patch_size": 1, |
| "audio_patch_token": 128256, |
| "audio_token_len": 750, |
| "audio_tower": "openai/whisper-large-v2", |
| "bos_token_id": 128000, |
| "eos_token_id": [ |
| 128001, |
| 128008, |
| 128009 |
| ], |
| "hidden_act": "silu", |
| "hidden_size": 4096, |
| "initializer_range": 0.02, |
| "intermediate_size": 14336, |
| "llm_pad_token_id": 128009, |
| "max_position_embeddings": 131072, |
| "mlp_bias": false, |
| "model_type": "Soundwave", |
| "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": "4.43.1", |
| "use_cache": false, |
| "vocab_size": 128257 |
| } |
|
|
