From 9711bfbb62df4f73f18eea1dd7adc580dffaa10f Mon Sep 17 00:00:00 2001
From: Robert Shaw <rshaw@neuralmagic>
Date: Thu, 27 Jun 2024 02:40:10 +0000
Subject: [PATCH] fix bad merge

---
 .../nm-run-lm-eval-gsm-vllm-baseline.sh       | 52 -------------------
 1 file changed, 52 deletions(-)

diff --git a/.github/scripts/nm-run-lm-eval-gsm-vllm-baseline.sh b/.github/scripts/nm-run-lm-eval-gsm-vllm-baseline.sh
index c2223635a90a3..d6b38752945ce 100644
--- a/.github/scripts/nm-run-lm-eval-gsm-vllm-baseline.sh
+++ b/.github/scripts/nm-run-lm-eval-gsm-vllm-baseline.sh
@@ -49,55 +49,3 @@ lm_eval --model vllm \
   --model_args pretrained=$MODEL,tensor_parallel_size=$TP_SIZE \
   --tasks gsm8k --num_fewshot $FEWSHOT --limit $LIMIT \
   --batch_size $BATCH_SIZE
-
-#!/bin/bash
-# We can use this script to compute baseline accuracy on GSM for vllm.
-# We use this for fp8, which HF does not support.
-#
-# Make sure you have lm-eval-harness installed:
-#   pip install git+https://github.com/EleutherAI/lm-evaluation-harness.git@9516087b81a61d0e220b22cc1b75be76de23bc10
-
-usage() {
-    echo``
-    echo "Runs lm eval harness on GSM8k using huggingface transformers."
-    echo "This pathway is intended to be used to create baselines for "
-    echo "our automated nm-test-accuracy workflow"
-    echo
-    echo "usage: ${0} <options>"
-    echo
-    echo "  -m    - huggingface stub or local directory of the model"
-    echo "  -b    - batch size to run the evaluation at"
-    echo "  -l    - limit number of samples to run"
-    echo "  -f    - number of fewshot samples to use"
-    echo "  -t    - tensor parallel size to run at"
-    echo
-}
-
-while getopts "m:b:l:f:t:" OPT; do
-  case ${OPT} in
-    m ) 
-        MODEL="$OPTARG"
-        ;;
-    b ) 
-        BATCH_SIZE="$OPTARG"
-        ;;
-    l ) 
-        LIMIT="$OPTARG"
-        ;;
-    f ) 
-        FEWSHOT="$OPTARG"
-        ;;
-    t )
-        TP_SIZE="$OPTARG"
-        ;;
-    \? ) 
-        usage
-        exit 1
-        ;;
-  esac
-done
-
-lm_eval --model vllm \
-  --model_args pretrained=$MODEL,tensor_parallel_size=$TP_SIZE \
-  --tasks gsm8k --num_fewshot $FEWSHOT --limit $LIMIT \
-  --batch_size $BATCH_SIZE