kaitchup
/

GLM-4.7-Flash-FP8-Dynamic

compressed-tensors

Model card Files Files and versions

GLM-4.7-Flash-FP8-Dynamic / recipe.yaml

bnjmnmarie's picture

Upload folder using huggingface_hub

231c5f2 verified about 1 month ago

history blame contribute delete

235 Bytes

	default_stage:
	default_modifiers:
	QuantizationModifier:
	targets: [Linear]
	ignore: [lm_head, model.embed_tokens, 're:.input_layernorm$', 're:.post_attention_layernorm$',
	model.norm]
	scheme: FP8_DYNAMIC