初始化项目,由ModelHub XC社区提供模型
Model: neuralmagic/Meta-Llama-3.1-8B-Instruct-FP8-dynamic Source: Original Platform
This commit is contained in:
9
recipe.yaml
Normal file
9
recipe.yaml
Normal file
@@ -0,0 +1,9 @@
|
||||
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]
|
||||
Reference in New Issue
Block a user