Audio-Text-to-Text
ONNX
Safetensors
English
Chinese
Model Optimizer
bailing_moe_v3_audio
audio
speech
automatic-speech-recognition
audio-understanding
audio-reasoning
speech-to-text
conversational
mixture-of-experts
quantized
nvfp4
fp4
4-bit precision
modelopt
blackwell
custom_code
Eval Results (legacy)
Eval Results
| { | |
| "producer": { | |
| "name": "modelopt", | |
| "version": "0.47.0" | |
| }, | |
| "quantization": { | |
| "quant_algo": "NVFP4", | |
| "kv_cache_quant_algo": null, | |
| "group_size": 16, | |
| "exclude_modules": [ | |
| "linear_proj_audio*", | |
| "lm_head", | |
| "model.audio*", | |
| "model.layers.0*", | |
| "model.layers.1.attention*", | |
| "model.layers.1.mlp.gate", | |
| "model.layers.1.mlp.shared_experts*", | |
| "model.layers.10*", | |
| "model.layers.11.attention*", | |
| "model.layers.11.mlp.gate", | |
| "model.layers.11.mlp.shared_experts*", | |
| "model.layers.12.attention*", | |
| "model.layers.12.mlp.gate", | |
| "model.layers.12.mlp.shared_experts*", | |
| "model.layers.13.attention*", | |
| "model.layers.13.mlp.gate", | |
| "model.layers.13.mlp.shared_experts*", | |
| "model.layers.14.attention*", | |
| "model.layers.14.mlp.gate", | |
| "model.layers.14.mlp.shared_experts*", | |
| "model.layers.15*", | |
| "model.layers.16.attention*", | |
| "model.layers.16.mlp.gate", | |
| "model.layers.16.mlp.shared_experts*", | |
| "model.layers.17.attention*", | |
| "model.layers.17.mlp.gate", | |
| "model.layers.17.mlp.shared_experts*", | |
| "model.layers.18*", | |
| "model.layers.19.attention*", | |
| "model.layers.19.mlp.gate", | |
| "model.layers.19.mlp.shared_experts*", | |
| "model.layers.2.attention*", | |
| "model.layers.2.mlp.gate", | |
| "model.layers.2.mlp.shared_experts*", | |
| "model.layers.20*", | |
| "model.layers.21*", | |
| "model.layers.22*", | |
| "model.layers.23.attention*", | |
| "model.layers.23.mlp.gate", | |
| "model.layers.23.mlp.shared_experts*", | |
| "model.layers.24*", | |
| "model.layers.3.attention*", | |
| "model.layers.3.mlp.gate", | |
| "model.layers.3.mlp.shared_experts*", | |
| "model.layers.4.attention*", | |
| "model.layers.4.mlp.gate", | |
| "model.layers.4.mlp.shared_experts*", | |
| "model.layers.5*", | |
| "model.layers.6.attention*", | |
| "model.layers.6.mlp.gate", | |
| "model.layers.6.mlp.shared_experts*", | |
| "model.layers.7.attention*", | |
| "model.layers.7.mlp.gate", | |
| "model.layers.7.mlp.shared_experts*", | |
| "model.layers.8.attention*", | |
| "model.layers.8.mlp.gate", | |
| "model.layers.8.mlp.shared_experts*", | |
| "model.layers.9.attention*", | |
| "model.layers.9.mlp.gate", | |
| "model.layers.9.mlp.shared_experts*", | |
| "model.word_embeddings", | |
| "model.layers.24.*" | |
| ] | |
| } | |
| } |