SinclairSchneider's picture
Duplicate from canada-quant/DeepSeek-V4-Flash-W4A16-FP8-MTP
ba2f0e7
Raw
History Blame Contribute Delete
2.06 kB
default_stage:
default_modifiers:
GPTQModifier:
config_groups:
attention:
targets: ['re:^model\.layers\.\d+\.self_attn\.(q_a_proj|q_b_proj|kv_proj|o_a_proj|o_b_proj)$',
're:^model\.layers\.\d+\.self_attn\.compressor\.(gate_proj|kv_proj)$', 're:^model\.layers\.\d+\.self_attn\.compressor\.indexer\.(gate_proj|kv_proj|q_b_proj|weights_proj)$']
weights:
num_bits: 8
type: float
symmetric: true
group_size: null
strategy: block
block_structure: [128, 128]
dynamic: false
actorder: null
scale_dtype: null
zp_dtype: null
observer: memoryless_minmax
observer_kwargs: {}
input_activations:
num_bits: 8
type: float
symmetric: true
group_size: 128
strategy: group
block_structure: null
dynamic: true
actorder: null
scale_dtype: null
zp_dtype: null
observer: null
observer_kwargs: {}
output_activations: null
format: null
experts:
targets: ['re:^model\.layers\.\d+\.mlp\.experts\.\d+\.(gate_proj|up_proj|down_proj)$']
weights:
num_bits: 4
type: int
symmetric: true
group_size: 128
strategy: group
block_structure: null
dynamic: false
actorder: !!python/object/apply:compressed_tensors.quantization.quant_args.ActivationOrdering [
static]
scale_dtype: null
zp_dtype: null
observer: memoryless_minmax
observer_kwargs: {}
input_activations: null
output_activations: null
format: null
targets: [Linear]
ignore: [lm_head, 're:.*mtp\..*']
bypass_divisibility_checks: false
block_size: 128
dampening_frac: 0.1
actorder: static
offload_hessians: true