espressor
/

meta-llama.Llama-2-7b-chat-hf_W4A16

Text Generation

text-generation-inference

Inference Endpoints

compressed-tensors

Model card Files Files and versions Community

meta-llama.Llama-2-7b-chat-hf_W4A16 / recipe.yaml

xzyao's picture

Upload folder using huggingface_hub

f997c76 verified 30 days ago

history blame contribute delete

120 Bytes

	DEFAULT_stage:
	DEFAULT_modifiers:
	GPTQModifier:
	targets: Linear
	ignore: [lm_head]
	scheme: W4A16