| { | |
| "architectures": [ | |
| "VoxtralRealtimeForConditionalGeneration" | |
| ], | |
| "audio_config": { | |
| "activation_function": "gelu", | |
| "attention_dropout": 0.0, | |
| "head_dim": 64, | |
| "hidden_act": "silu", | |
| "hidden_size": 1280, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 5120, | |
| "max_position_embeddings": 1500, | |
| "model_type": "voxtral_realtime_encoder", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 32, | |
| "num_mel_bins": 128, | |
| "rms_norm_eps": 1e-05, | |
| "rope_parameters": { | |
| "rope_theta": 1000000.0, | |
| "rope_type": "default" | |
| }, | |
| "sliding_window": 750, | |
| "vocab_size": 131072 | |
| }, | |
| "audio_length_per_tok": 8, | |
| "default_num_delay_tokens": 6, | |
| "downsample_factor": 4, | |
| "dtype": "bfloat16", | |
| "hidden_size": 3072, | |
| "model_type": "voxtral_realtime", | |
| "projector_hidden_act": "gelu", | |
| "text_config": { | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 3072, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 9216, | |
| "max_position_embeddings": 131072, | |
| "model_type": "voxtral_realtime_text", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 26, | |
| "num_key_value_heads": 8, | |
| "pad_token_id": null, | |
| "rms_norm_eps": 1e-05, | |
| "rope_parameters": { | |
| "rope_theta": 1000000.0, | |
| "rope_type": "default" | |
| }, | |
| "sliding_window": 8192, | |
| "tie_word_embeddings": true, | |
| "use_cache": true, | |
| "vocab_size": 131072 | |
| }, | |
| "transformers_version": "5.2.0.dev0" | |
| } | |