GaMS3-12B-Instruct-Lex-NVFP4 / hf_quant_config.json
tknez's picture
Upload GaMS3-12B-Instruct-Lex quantized to NVFP4 format
5d9b2ac verified
Raw History Blame Contribute Delete
268 Bytes
{
"producer": {
"name": "modelopt",
"version": "0.48.0"
},
"quantization": {
"quant_algo": "NVFP4",
"kv_cache_quant_algo": "FP8",
"group_size": 16,
"exclude_modules": [
"lm_head"
]
}
}