Meta-Llama-3.1-8B-FP8 / recipe.yaml
Lin-K76's picture
Upload folder using huggingface_hub
b9c19e4 verified
raw
history blame
364 Bytes
quant_stage:
quant_modifiers:
QuantizationModifier:
ignore: [lm_head]
config_groups:
group_0:
weights: {num_bits: 8, type: float, strategy: tensor, dynamic: false, symmetric: true}
input_activations: {num_bits: 8, type: float, strategy: tensor, dynamic: false,
symmetric: true}
targets: [Linear]