13 lines
512 B
YAML
13 lines
512 B
YAML
quant_stage:
|
|
quant_modifiers:
|
|
GPTQModifier:
|
|
dampening_frac: 0.01
|
|
ignore: ['re:.*lm_head.*', 're:.*embed_tokens.*', 're:vision_tower.*', 're:multi_modal_projector.*']
|
|
sequential_update: true
|
|
config_groups:
|
|
group_0:
|
|
targets: [Linear]
|
|
weights: {num_bits: 8, type: int, symmetric: true, strategy: channel, observer: mse}
|
|
input_activations: {num_bits: 8, type: int, symmetric: true, strategy: token, dynamic: true,
|
|
observer: memoryless}
|