Files
Llama-3.2-1B-Instruct-FP8-d…/recipe.yaml

10 lines
351 B
YAML
Raw Normal View History

quant_stage:
quant_modifiers:
QuantizationModifier:
ignore: [lm_head]
config_groups:
group_0:
weights: {num_bits: 8, type: float, strategy: channel, dynamic: false, symmetric: true}
input_activations: {num_bits: 8, type: float, strategy: token, dynamic: true, symmetric: true}
targets: [Linear]