tencent
/

Hunyuan-MT-7B-fp8

hunyuan_v1_dense

text-generation

compressed-tensors

Model card Files Files and versions

Hunyuan-MT-7B-fp8 / hf_quant_config.json

hhoh's picture

Upload hf_quant_config.json with huggingface_hub

3bb8531 verified 3 days ago

192 Bytes

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