sadkins65's picture
Upload folder using huggingface_hub
a8fce7b verified
raw
history blame
339 Bytes
quant_stage:
quant_modifiers:
GPTQModifier:
sequential_update: false
ignore: [lm_head]
config_groups:
group_0:
weights: {num_bits: 8, type: int, symmetric: true, strategy: tensor}
input_activations: {num_bits: 8, type: int, symmetric: true, strategy: tensor}
targets: [Linear]