Instructions to use onnx-community/Voxtral-Mini-3B-2507-ONNX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers.js
How to use onnx-community/Voxtral-Mini-3B-2507-ONNX with Transformers.js:
// npm i @huggingface/transformers import { pipeline } from '@huggingface/transformers'; // Allocate pipeline const pipe = await pipeline('audio-text-to-text', 'onnx-community/Voxtral-Mini-3B-2507-ONNX');
| { | |
| "architectures": [ | |
| "VoxtralForConditionalGeneration" | |
| ], | |
| "audio_config": { | |
| "activation_dropout": 0.0, | |
| "activation_function": "gelu", | |
| "attention_dropout": 0.0, | |
| "dropout": 0.0, | |
| "head_dim": 64, | |
| "hidden_size": 1280, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 5120, | |
| "layerdrop": 0.0, | |
| "max_source_positions": 1500, | |
| "model_type": "voxtral_encoder", | |
| "num_attention_heads": 20, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 20, | |
| "num_mel_bins": 128, | |
| "scale_embedding": false, | |
| "vocab_size": 51866 | |
| }, | |
| "audio_token_id": 24, | |
| "hidden_size": 3072, | |
| "model_type": "voxtral", | |
| "projector_hidden_act": "gelu", | |
| "text_config": { | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 3072, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 8192, | |
| "max_position_embeddings": 131072, | |
| "mlp_bias": false, | |
| "model_type": "llama", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 30, | |
| "num_key_value_heads": 8, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": null, | |
| "rope_theta": 100000000.0, | |
| "sliding_window": null, | |
| "use_cache": true, | |
| "vocab_size": 131072 | |
| }, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.54.0.dev0", | |
| "transformers.js_config": { | |
| "dtype": { | |
| "embed_tokens": "fp16" | |
| }, | |
| "kv_cache_dtype": { | |
| "q4f16": "float16", | |
| "fp16": "float16" | |
| }, | |
| "use_external_data_format": { | |
| "audio_encoder.onnx": 2, | |
| "audio_encoder_fp16.onnx": 1, | |
| "audio_encoder_int8.onnx": 1, | |
| "audio_encoder_uint8.onnx": 1, | |
| "audio_encoder_quantized.onnx": 1, | |
| "audio_encoder_q4.onnx": 1, | |
| "audio_encoder_q4f16.onnx": 1, | |
| "audio_encoder_bnb4.onnx": 1, | |
| "decoder_model_merged.onnx": 8, | |
| "decoder_model_merged_fp16.onnx": 4, | |
| "decoder_model_merged_q4.onnx": 2, | |
| "decoder_model_merged_q4f16.onnx": 1, | |
| "embed_tokens.onnx": 1, | |
| "embed_tokens_fp16.onnx": 1, | |
| "embed_tokens_quantized.onnx": 1, | |
| "embed_tokens_q4.onnx": 1 | |
| } | |
| }, | |
| "vocab_size": 131072 | |
| } |