NVIDIA-Nemotron-3-Nano-30B-A3B-FP8 / hf_quant_config.json
suhara's picture
Upload folder using huggingface_hub
f9a1d7f verified
raw
history blame
3.05 kB
{
"producer": {
"name": "modelopt",
"version": "0.29.0"
},
"quantization": {
"quant_algo": "FP8",
"kv_cache_quant_algo": "FP8",
"group_size": 16,
"exclude_modules": [
"lm_head",
"backbone.layers.4.mixer.in_proj",
"backbone.layers.4.mixer.out_proj",
"backbone.layers.5.mixer.q_proj",
"backbone.layers.5.mixer.k_proj",
"backbone.layers.5.mixer.v_proj",
"backbone.layers.5.mixer.o_proj",
"backbone.layers.11.mixer.in_proj",
"backbone.layers.11.mixer.out_proj",
"backbone.layers.12.mixer.q_proj",
"backbone.layers.12.mixer.k_proj",
"backbone.layers.12.mixer.v_proj",
"backbone.layers.12.mixer.o_proj",
"backbone.layers.18.mixer.in_proj",
"backbone.layers.18.mixer.out_proj",
"backbone.layers.19.mixer.q_proj",
"backbone.layers.19.mixer.k_proj",
"backbone.layers.19.mixer.v_proj",
"backbone.layers.19.mixer.o_proj",
"backbone.layers.25.mixer.in_proj",
"backbone.layers.25.mixer.out_proj",
"backbone.layers.26.mixer.q_proj",
"backbone.layers.26.mixer.k_proj",
"backbone.layers.26.mixer.v_proj",
"backbone.layers.26.mixer.o_proj",
"backbone.layers.32.mixer.in_proj",
"backbone.layers.32.mixer.out_proj",
"backbone.layers.33.mixer.q_proj",
"backbone.layers.33.mixer.k_proj",
"backbone.layers.33.mixer.v_proj",
"backbone.layers.33.mixer.o_proj",
"backbone.layers.41.mixer.in_proj",
"backbone.layers.41.mixer.out_proj",
"backbone.layers.42.mixer.q_proj",
"backbone.layers.42.mixer.k_proj",
"backbone.layers.42.mixer.v_proj",
"backbone.layers.42.mixer.o_proj",
"backbone.layers.0.mixer.conv1d",
"backbone.layers.2.mixer.conv1d",
"backbone.layers.4.mixer.conv1d",
"backbone.layers.7.mixer.conv1d",
"backbone.layers.9.mixer.conv1d",
"backbone.layers.11.mixer.conv1d",
"backbone.layers.14.mixer.conv1d",
"backbone.layers.16.mixer.conv1d",
"backbone.layers.18.mixer.conv1d",
"backbone.layers.21.mixer.conv1d",
"backbone.layers.23.mixer.conv1d",
"backbone.layers.25.mixer.conv1d",
"backbone.layers.28.mixer.conv1d",
"backbone.layers.30.mixer.conv1d",
"backbone.layers.32.mixer.conv1d",
"backbone.layers.35.mixer.conv1d",
"backbone.layers.37.mixer.conv1d",
"backbone.layers.39.mixer.conv1d",
"backbone.layers.41.mixer.conv1d",
"backbone.layers.44.mixer.conv1d",
"backbone.layers.46.mixer.conv1d",
"backbone.layers.48.mixer.conv1d",
"backbone.layers.50.mixer.conv1d"
]
}
}