GLM-5.3-Flash-NVFP4 / hf_quant_config.json
JustinTong's picture
Release GLM-5.3-Flash-NVFP4
e30b02f
Raw
History Blame Contribute Delete
7.23 kB
{
"producer": {
"name": "modelopt",
"version": "0.46.0"
},
"quantization": {
"exclude_modules": [
"lm_head",
"model.language_model.embed_tokens",
"model.language_model.layers.0.self_attn*",
"model.language_model.layers.1.self_attn*",
"model.language_model.layers.10.mlp.gate",
"model.language_model.layers.10.self_attn*",
"model.language_model.layers.11.mlp.gate",
"model.language_model.layers.11.self_attn*",
"model.language_model.layers.12.mlp.gate",
"model.language_model.layers.12.self_attn*",
"model.language_model.layers.13.mlp.gate",
"model.language_model.layers.13.self_attn*",
"model.language_model.layers.14.mlp.gate",
"model.language_model.layers.14.self_attn*",
"model.language_model.layers.15.mlp.gate",
"model.language_model.layers.15.self_attn*",
"model.language_model.layers.16.mlp.gate",
"model.language_model.layers.16.self_attn*",
"model.language_model.layers.17.mlp.gate",
"model.language_model.layers.17.self_attn*",
"model.language_model.layers.18.mlp.gate",
"model.language_model.layers.18.self_attn*",
"model.language_model.layers.19.mlp.gate",
"model.language_model.layers.19.self_attn*",
"model.language_model.layers.2.self_attn*",
"model.language_model.layers.20.mlp.gate",
"model.language_model.layers.20.self_attn*",
"model.language_model.layers.21.mlp.gate",
"model.language_model.layers.21.self_attn*",
"model.language_model.layers.22.mlp.gate",
"model.language_model.layers.22.self_attn*",
"model.language_model.layers.23.mlp.gate",
"model.language_model.layers.23.self_attn*",
"model.language_model.layers.24.mlp.gate",
"model.language_model.layers.24.self_attn*",
"model.language_model.layers.25.mlp.gate",
"model.language_model.layers.25.self_attn*",
"model.language_model.layers.26.mlp.gate",
"model.language_model.layers.26.self_attn*",
"model.language_model.layers.27.mlp.gate",
"model.language_model.layers.27.self_attn*",
"model.language_model.layers.28.mlp.gate",
"model.language_model.layers.28.self_attn*",
"model.language_model.layers.29.mlp.gate",
"model.language_model.layers.29.self_attn*",
"model.language_model.layers.3.mlp.gate",
"model.language_model.layers.3.self_attn*",
"model.language_model.layers.30.mlp.gate",
"model.language_model.layers.30.self_attn*",
"model.language_model.layers.31.mlp.gate",
"model.language_model.layers.31.self_attn*",
"model.language_model.layers.32.mlp.gate",
"model.language_model.layers.32.self_attn*",
"model.language_model.layers.33.mlp.gate",
"model.language_model.layers.33.self_attn*",
"model.language_model.layers.34.mlp.gate",
"model.language_model.layers.34.self_attn*",
"model.language_model.layers.35.mlp.gate",
"model.language_model.layers.35.self_attn*",
"model.language_model.layers.36.mlp.gate",
"model.language_model.layers.36.self_attn*",
"model.language_model.layers.37.mlp.gate",
"model.language_model.layers.37.self_attn*",
"model.language_model.layers.38.mlp.gate",
"model.language_model.layers.38.self_attn*",
"model.language_model.layers.39.mlp.gate",
"model.language_model.layers.39.self_attn*",
"model.language_model.layers.4.mlp.gate",
"model.language_model.layers.4.self_attn*",
"model.language_model.layers.40.mlp.gate",
"model.language_model.layers.40.self_attn*",
"model.language_model.layers.41.mlp.gate",
"model.language_model.layers.41.self_attn*",
"model.language_model.layers.42.mlp.gate",
"model.language_model.layers.42.self_attn*",
"model.language_model.layers.43.mlp.gate",
"model.language_model.layers.43.self_attn*",
"model.language_model.layers.44.mlp.gate",
"model.language_model.layers.44.self_attn*",
"model.language_model.layers.5.mlp.gate",
"model.language_model.layers.5.self_attn*",
"model.language_model.layers.6.mlp.gate",
"model.language_model.layers.6.self_attn*",
"model.language_model.layers.7.mlp.gate",
"model.language_model.layers.7.self_attn*",
"model.language_model.layers.8.mlp.gate",
"model.language_model.layers.8.self_attn*",
"model.language_model.layers.9.mlp.gate",
"model.language_model.layers.9.self_attn*",
"model.visual*",
"model.embed_tokens",
"model.layers.0.self_attn*",
"model.layers.1.self_attn*",
"model.layers.10.mlp.gate",
"model.layers.10.self_attn*",
"model.layers.11.mlp.gate",
"model.layers.11.self_attn*",
"model.layers.12.mlp.gate",
"model.layers.12.self_attn*",
"model.layers.13.mlp.gate",
"model.layers.13.self_attn*",
"model.layers.14.mlp.gate",
"model.layers.14.self_attn*",
"model.layers.15.mlp.gate",
"model.layers.15.self_attn*",
"model.layers.16.mlp.gate",
"model.layers.16.self_attn*",
"model.layers.17.mlp.gate",
"model.layers.17.self_attn*",
"model.layers.18.mlp.gate",
"model.layers.18.self_attn*",
"model.layers.19.mlp.gate",
"model.layers.19.self_attn*",
"model.layers.2.self_attn*",
"model.layers.20.mlp.gate",
"model.layers.20.self_attn*",
"model.layers.21.mlp.gate",
"model.layers.21.self_attn*",
"model.layers.22.mlp.gate",
"model.layers.22.self_attn*",
"model.layers.23.mlp.gate",
"model.layers.23.self_attn*",
"model.layers.24.mlp.gate",
"model.layers.24.self_attn*",
"model.layers.25.mlp.gate",
"model.layers.25.self_attn*",
"model.layers.26.mlp.gate",
"model.layers.26.self_attn*",
"model.layers.27.mlp.gate",
"model.layers.27.self_attn*",
"model.layers.28.mlp.gate",
"model.layers.28.self_attn*",
"model.layers.29.mlp.gate",
"model.layers.29.self_attn*",
"model.layers.3.mlp.gate",
"model.layers.3.self_attn*",
"model.layers.30.mlp.gate",
"model.layers.30.self_attn*",
"model.layers.31.mlp.gate",
"model.layers.31.self_attn*",
"model.layers.32.mlp.gate",
"model.layers.32.self_attn*",
"model.layers.33.mlp.gate",
"model.layers.33.self_attn*",
"model.layers.34.mlp.gate",
"model.layers.34.self_attn*",
"model.layers.35.mlp.gate",
"model.layers.35.self_attn*",
"model.layers.36.mlp.gate",
"model.layers.36.self_attn*",
"model.layers.37.mlp.gate",
"model.layers.37.self_attn*",
"model.layers.38.mlp.gate",
"model.layers.38.self_attn*",
"model.layers.39.mlp.gate",
"model.layers.39.self_attn*",
"model.layers.4.mlp.gate",
"model.layers.4.self_attn*",
"model.layers.40.mlp.gate",
"model.layers.40.self_attn*",
"model.layers.41.mlp.gate",
"model.layers.41.self_attn*",
"model.layers.42.mlp.gate",
"model.layers.42.self_attn*",
"model.layers.43.mlp.gate",
"model.layers.43.self_attn*",
"model.layers.44.mlp.gate",
"model.layers.44.self_attn*",
"model.layers.5.mlp.gate",
"model.layers.5.self_attn*",
"model.layers.6.mlp.gate",
"model.layers.6.self_attn*",
"model.layers.7.mlp.gate",
"model.layers.7.self_attn*",
"model.layers.8.mlp.gate",
"model.layers.8.self_attn*",
"model.layers.9.mlp.gate",
"model.layers.9.self_attn*",
"model.language_model.layers.45*",
"model.layers.45*",
"model.decoder*",
"visual*"
],
"group_size": 16,
"kv_cache_quant_algo": null,
"quant_algo": "NVFP4"
}
}