Evaluation pipeline points to missing files
Closed this issue · 2 comments
snps-tonatiuh commented
I am following the README to evaluate a model with
CUDA_VISIBLE_DEVICES=0 python main_block_ap.py \
--resume_quant ./output/pre_quantized_models/Llama-2-7b-EfficientQAT-w2g64 \
--net Llama-2 \
--wbits 2 \
--group_size 64 \
--output_dir ./output/inference_results/ \
--eval_ppl \
--eval_tasks piqa,arc_easy,arc_challenge,hellaswag,winogrande
But I get an error due to hard-coded file locations:
FileNotFoundError: Unable to find '/cpfs01/user/chenmengzhao/huggingface/datasets/allenai___json/allenai--c4-6fbe877195f42de5/0.0.0/0f7e3662623656454fcd2b650f34e886a7db4b9104504885bd462096cc7a9f51/json-train-00000-of-00002.arrow'
ChenMnZ commented
You can delete the following code to solve this problem.
EfficientQAT/datautils_block.py
Lines 47 to 60 in 346d98a
I have wrapped such code with
try & except
, it is curious to report error.snps-tonatiuh commented
I don't understand why the try, except
block did not work as expected, but thanks anyways.