| { | |
| "_name_or_path": "fixie-ai/ultravox-v0_5-llama-3_2-1b", | |
| "architectures": [ | |
| "UltravoxModel" | |
| ], | |
| "audio_config": { | |
| "_name_or_path": "openai/whisper-large-v3-turbo", | |
| "activation_dropout": 0.0, | |
| "activation_function": "gelu", | |
| "apply_spec_augment": false, | |
| "architectures": [ | |
| "WhisperForConditionalGeneration" | |
| ], | |
| "attention_dropout": 0.0, | |
| "begin_suppress_tokens": [ | |
| 220, | |
| 50256 | |
| ], | |
| "bos_token_id": 50257, | |
| "d_model": 1280, | |
| "decoder_attention_heads": 20, | |
| "decoder_ffn_dim": 5120, | |
| "decoder_layerdrop": 0.0, | |
| "decoder_layers": 4, | |
| "decoder_start_token_id": 50258, | |
| "dropout": 0.0, | |
| "encoder_attention_heads": 20, | |
| "encoder_ffn_dim": 5120, | |
| "encoder_layerdrop": 0.0, | |
| "encoder_layers": 32, | |
| "eos_token_id": 50257, | |
| "init_std": 0.02, | |
| "is_encoder_decoder": true, | |
| "max_source_positions": 1500, | |
| "max_target_positions": 448, | |
| "median_filter_width": 7, | |
| "model_type": "whisper", | |
| "num_hidden_layers": 32, | |
| "num_mel_bins": 128, | |
| "pad_token_id": 50257, | |
| "scale_embedding": false, | |
| "torch_dtype": "float16", | |
| "use_cache": true, | |
| "vocab_size": 51866 | |
| }, | |
| "audio_latency_block_size": null, | |
| "audio_model_id": null, | |
| "hidden_size": 4096, | |
| "ignore_index": -100, | |
| "initializer_range": 0.02, | |
| "model_type": "ultravox", | |
| "norm_init": 0.4, | |
| "pad_token_id": 128009, | |
| "projector_act": "swiglu", | |
| "projector_ln_mid": true, | |
| "stack_factor": 8, | |
| "text_config": { | |
| "architectures": [ | |
| "LlamaForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 128000, | |
| "eos_token_id": [ | |
| 128001, | |
| 128008, | |
| 128009 | |
| ], | |
| "head_dim": 64, | |
| "hidden_act": "silu", | |
| "hidden_size": 2048, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 8192, | |
| "max_position_embeddings": 131072, | |
| "mlp_bias": false, | |
| "model_type": "llama", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 16, | |
| "num_key_value_heads": 8, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": { | |
| "factor": 32.0, | |
| "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": true, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.45.0.dev0", | |
| "use_cache": true, | |
| "vocab_size": 128256 | |
| }, | |
| "text_model_id": "meta-llama/Llama-3.2-1B-Instruct", | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.48.1", | |
| "transformers.js_config": { | |
| "kv_cache_dtype": { | |
| "q4f16": "float16", | |
| "fp16": "float16" | |
| } | |
| }, | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 16, | |
| "vocab_size": 128256 | |
| } |