DeepSeek-V4-Flash-NVFP4 / hf_quant_config.json
jingyux-nv's picture
Update config.json and hf_quant_config.json
7fc18be verified
Raw
History Blame
4.55 kB
{
"producer": {
"name": "modelopt",
"version": "dsv4-nvfp4-experts"
},
"quantization": {
"quant_algo": "MIXED_PRECISION",
"kv_cache_quant_algo": null,
"group_size": 16,
"quantized_layers": {
"layers.0.ffn.experts": {
"quant_algo": "NVFP4",
"group_size": 16
},
"layers.1.ffn.experts": {
"quant_algo": "NVFP4",
"group_size": 16
},
"layers.10.ffn.experts": {
"quant_algo": "NVFP4",
"group_size": 16
},
"layers.11.ffn.experts": {
"quant_algo": "NVFP4",
"group_size": 16
},
"layers.12.ffn.experts": {
"quant_algo": "NVFP4",
"group_size": 16
},
"layers.13.ffn.experts": {
"quant_algo": "NVFP4",
"group_size": 16
},
"layers.14.ffn.experts": {
"quant_algo": "NVFP4",
"group_size": 16
},
"layers.15.ffn.experts": {
"quant_algo": "NVFP4",
"group_size": 16
},
"layers.16.ffn.experts": {
"quant_algo": "NVFP4",
"group_size": 16
},
"layers.17.ffn.experts": {
"quant_algo": "NVFP4",
"group_size": 16
},
"layers.18.ffn.experts": {
"quant_algo": "NVFP4",
"group_size": 16
},
"layers.19.ffn.experts": {
"quant_algo": "NVFP4",
"group_size": 16
},
"layers.2.ffn.experts": {
"quant_algo": "NVFP4",
"group_size": 16
},
"layers.20.ffn.experts": {
"quant_algo": "NVFP4",
"group_size": 16
},
"layers.21.ffn.experts": {
"quant_algo": "NVFP4",
"group_size": 16
},
"layers.22.ffn.experts": {
"quant_algo": "NVFP4",
"group_size": 16
},
"layers.23.ffn.experts": {
"quant_algo": "NVFP4",
"group_size": 16
},
"layers.24.ffn.experts": {
"quant_algo": "NVFP4",
"group_size": 16
},
"layers.25.ffn.experts": {
"quant_algo": "NVFP4",
"group_size": 16
},
"layers.26.ffn.experts": {
"quant_algo": "NVFP4",
"group_size": 16
},
"layers.27.ffn.experts": {
"quant_algo": "NVFP4",
"group_size": 16
},
"layers.28.ffn.experts": {
"quant_algo": "NVFP4",
"group_size": 16
},
"layers.29.ffn.experts": {
"quant_algo": "NVFP4",
"group_size": 16
},
"layers.3.ffn.experts": {
"quant_algo": "NVFP4",
"group_size": 16
},
"layers.30.ffn.experts": {
"quant_algo": "NVFP4",
"group_size": 16
},
"layers.31.ffn.experts": {
"quant_algo": "NVFP4",
"group_size": 16
},
"layers.32.ffn.experts": {
"quant_algo": "NVFP4",
"group_size": 16
},
"layers.33.ffn.experts": {
"quant_algo": "NVFP4",
"group_size": 16
},
"layers.34.ffn.experts": {
"quant_algo": "NVFP4",
"group_size": 16
},
"layers.35.ffn.experts": {
"quant_algo": "NVFP4",
"group_size": 16
},
"layers.36.ffn.experts": {
"quant_algo": "NVFP4",
"group_size": 16
},
"layers.37.ffn.experts": {
"quant_algo": "NVFP4",
"group_size": 16
},
"layers.38.ffn.experts": {
"quant_algo": "NVFP4",
"group_size": 16
},
"layers.39.ffn.experts": {
"quant_algo": "NVFP4",
"group_size": 16
},
"layers.4.ffn.experts": {
"quant_algo": "NVFP4",
"group_size": 16
},
"layers.40.ffn.experts": {
"quant_algo": "NVFP4",
"group_size": 16
},
"layers.41.ffn.experts": {
"quant_algo": "NVFP4",
"group_size": 16
},
"layers.42.ffn.experts": {
"quant_algo": "NVFP4",
"group_size": 16
},
"layers.5.ffn.experts": {
"quant_algo": "NVFP4",
"group_size": 16
},
"layers.6.ffn.experts": {
"quant_algo": "NVFP4",
"group_size": 16
},
"layers.7.ffn.experts": {
"quant_algo": "NVFP4",
"group_size": 16
},
"layers.8.ffn.experts": {
"quant_algo": "NVFP4",
"group_size": 16
},
"layers.9.ffn.experts": {
"quant_algo": "NVFP4",
"group_size": 16
}
},
"exclude_modules": [
"*.attn.*",
"*.ffn.shared_experts.*",
"head",
"mtp.*"
]
}
}