nm-testing
/

TinyLlama-1.1B-Chat-v1.0-FP8_DYNAMIC-e2e

Text Generation

text-generation-inference

Inference Endpoints

compressed-tensors

Model card Files Files and versions Community

TinyLlama-1.1B-Chat-v1.0-FP8_DYNAMIC-e2e / recipe.yaml

dsikka's picture

Upload folder using huggingface_hub

5abaf76 verified 29 days ago

136 Bytes

	DEFAULT_stage:
	DEFAULT_modifiers:
	QuantizationModifier:
	ignore: [lm_head]
	targets: [Linear]
	scheme: FP8_DYNAMIC