PTQ-Level Efficiency, QAT-Level Accuracy | 训练后量化的效率,量化感知训练的精度
fix incorrect setting for lm-head (#149)
wenhuach219da2beed45dd
diff --git a/examples/language-modeling/main.py b/examples/language-modeling/main.pyindex 841c9d2f0..3ef1fb452 100644--- a/examples/language-modeling/main.py+++ b/examples/language-modeling/main.py@@ -290,7 +290,7 @@ if __name__ == '__main__':f"supported currently")breakif args.quant_lm_head:- weight_config[lm_head_layer_name] = {"data_type": "int", "bits": 4, "group_size": 32}+ weight_config[lm_head_layer_name] = {"data_type": "int"}transformers_version = [int(item) for item in transformers.__version__.split('.')[:2]]if transformers_version[0] == 4 and transformers_version[1] < 38:error_message = "Please upgrade transformers>=4.38.0 to support lm-head quantization."