Skip to content

Commit 966aa9b

Browse files
committed
Update run_quant.sh
Signed-off-by: yuwenzho <[email protected]>
1 parent 595007b commit 966aa9b

File tree

1 file changed

+1
-1
lines changed
  • examples/onnxrt/nlp/huggingface_model/text_generation/llama/quantization/ptq_static

1 file changed

+1
-1
lines changed

examples/onnxrt/nlp/huggingface_model/text_generation/llama/quantization/ptq_static/run_quant.sh

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -70,7 +70,7 @@ function run_tuning {
7070
python main.py \
7171
--quant_format ${quant_format-QOperator} \
7272
--model_path ${input_model} \
73-
--tokenizer ${tokenizer-meta-llama/Llama-2-7b-hf} \
73+
--tokenizer ${tokenizer-meta-llama/Llama-2-7b-hf} \
7474
--output_model ${output_model} \
7575
--batch_size ${batch_size-1} \
7676
--smooth_quant_alpha ${alpha-0.6} \

0 commit comments

Comments
 (0)