AngelSlim
/

Glm4_6-fp8_static

compressed-tensors

Model card Files Files and versions

Glm4_6-fp8_static / hf_quant_config.json

woodchen7's picture

Upload hf_quant_config.json with huggingface_hub

370b74b verified 10 months ago

History Blame Contribute Delete

158 Bytes

	{
	"quantization": {
	"exclude_modules": [
	"lm_head"
	],
	"kv_cache_quant_algo": null,
	"quant_algo": "FP8"
	}
	}