Skip to content

Commit

Permalink
Merge pull request #1 from gshtras/v5.5_upstream_merge_rc
Browse files Browse the repository at this point in the history
V5.5 upstream merge rc
  • Loading branch information
gshtras authored Sep 4, 2024
2 parents c24a495 + 7fd46eb commit 19b1562
Show file tree
Hide file tree
Showing 975 changed files with 126,220 additions and 23,399 deletions.
2 changes: 1 addition & 1 deletion .buildkite/check-wheel-size.py
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
import os
import zipfile

MAX_SIZE_MB = 200
MAX_SIZE_MB = 250


def print_top_10_largest_files(zip_file):
Expand Down
18 changes: 0 additions & 18 deletions .buildkite/download-images.sh

This file was deleted.

12 changes: 12 additions & 0 deletions .buildkite/lm-eval-harness/configs/DeepSeek-V2-Lite-Chat.yaml
Original file line number Diff line number Diff line change
@@ -0,0 +1,12 @@
# bash ./run-lm-eval-gsm-vllm-baseline.sh -m deepseek-ai/DeepSeek-V2-Lite-Chat -b "auto" -l 1000 -f 5 -t 2
model_name: "deepseek-ai/DeepSeek-V2-Lite-Chat"
tasks:
- name: "gsm8k"
metrics:
- name: "exact_match,strict-match"
value: 0.671
- name: "exact_match,flexible-extract"
value: 0.664
limit: 1000
num_fewshot: 5
trust_remote_code: True
Original file line number Diff line number Diff line change
@@ -0,0 +1,11 @@
# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-hf-baseline.sh -m nm-testing/Meta-Llama-3-70B-Instruct-FBGEMM-nonuniform -b auto -l 1000 -f 5
model_name: "nm-testing/Meta-Llama-3-70B-Instruct-FBGEMM-nonuniform"
tasks:
- name: "gsm8k"
metrics:
- name: "exact_match,strict-match"
value: 0.905
- name: "exact_match,flexible-extract"
value: 0.905
limit: 1000
num_fewshot: 5
11 changes: 11 additions & 0 deletions .buildkite/lm-eval-harness/configs/Meta-Llama-3-70B-Instruct.yaml
Original file line number Diff line number Diff line change
@@ -0,0 +1,11 @@
# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-hf-baseline.sh -m meta-llama/Meta-Llama-3-70B-Instruct -b 32 -l 250 -f 5
model_name: "meta-llama/Meta-Llama-3-70B-Instruct"
tasks:
- name: "gsm8k"
metrics:
- name: "exact_match,strict-match"
value: 0.892
- name: "exact_match,flexible-extract"
value: 0.892
limit: 250
num_fewshot: 5
Original file line number Diff line number Diff line change
@@ -0,0 +1,11 @@
# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-vllm-baseline.sh -m nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors -b auto -l 1000 -f 5 -t 1
model_name: "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors"
tasks:
- name: "gsm8k"
metrics:
- name: "exact_match,strict-match"
value: 0.752
- name: "exact_match,flexible-extract"
value: 0.754
limit: 1000
num_fewshot: 5
Original file line number Diff line number Diff line change
@@ -0,0 +1,11 @@
# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-vllm-baseline.sh -m nm-testing/Meta-Llama-3-8B-Instruct-FBGEMM-nonuniform -b auto -l 1000 -f 5 -t 1
model_name: "nm-testing/Meta-Llama-3-8B-Instruct-FBGEMM-nonuniform"
tasks:
- name: "gsm8k"
metrics:
- name: "exact_match,strict-match"
value: 0.753
- name: "exact_match,flexible-extract"
value: 0.753
limit: 1000
num_fewshot: 5
Original file line number Diff line number Diff line change
@@ -0,0 +1,11 @@
# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-vllm-baseline.sh -m nm-testing/Meta-Llama-3-8B-FP8-compressed-tensors-test -b 32 -l 1000 -f 5 -t 1
model_name: "nm-testing/Meta-Llama-3-8B-FP8-compressed-tensors-test"
tasks:
- name: "gsm8k"
metrics:
- name: "exact_match,strict-match"
value: 0.755
- name: "exact_match,flexible-extract"
value: 0.755
limit: 1000
num_fewshot: 5
Original file line number Diff line number Diff line change
@@ -0,0 +1,11 @@
# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-vllm-baseline.sh -m neuralmagic/Meta-Llama-3-8B-Instruct-FP8 -b 32 -l 250 -f 5 -t 1
model_name: "neuralmagic/Meta-Llama-3-8B-Instruct-FP8"
tasks:
- name: "gsm8k"
metrics:
- name: "exact_match,strict-match"
value: 0.753
- name: "exact_match,flexible-extract"
value: 0.753
limit: 1000
num_fewshot: 5
Original file line number Diff line number Diff line change
@@ -0,0 +1,11 @@
# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-vllm-baseline.sh -m nm-testing/Meta-Llama-3-8B-Instruct-W8-Channel-A8-Dynamic-Per-Token-Test -b "auto" -l 250 -f 5 -t 1
model_name: "nm-testing/Meta-Llama-3-8B-Instruct-W8-Channel-A8-Dynamic-Per-Token-Test"
tasks:
- name: "gsm8k"
metrics:
- name: "exact_match,strict-match"
value: 0.728
- name: "exact_match,flexible-extract"
value: 0.728
limit: 250
num_fewshot: 5
Original file line number Diff line number Diff line change
@@ -0,0 +1,11 @@
# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-vllm-baseline.sh -m nm-testing/Meta-Llama-3-8B-Instruct-nonuniform-test -b auto -l 1000 -f 5 -t 1
model_name: "nm-testing/Meta-Llama-3-8B-Instruct-nonuniform-test"
tasks:
- name: "gsm8k"
metrics:
- name: "exact_match,strict-match"
value: 0.758
- name: "exact_match,flexible-extract"
value: 0.759
limit: 1000
num_fewshot: 5
11 changes: 11 additions & 0 deletions .buildkite/lm-eval-harness/configs/Meta-Llama-3-8B-Instruct.yaml
Original file line number Diff line number Diff line change
@@ -0,0 +1,11 @@
# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-hf-baseline.sh -m meta-llama/Meta-Llama-3-8B-Instruct -b 32 -l 250 -f 5 -t 1
model_name: "meta-llama/Meta-Llama-3-8B-Instruct"
tasks:
- name: "gsm8k"
metrics:
- name: "exact_match,strict-match"
value: 0.756
- name: "exact_match,flexible-extract"
value: 0.752
limit: 250
num_fewshot: 5
11 changes: 11 additions & 0 deletions .buildkite/lm-eval-harness/configs/Meta-Llama-3-8B-QQQ.yaml
Original file line number Diff line number Diff line change
@@ -0,0 +1,11 @@
# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-vllm-baseline.sh -m HandH1998/QQQ-Llama-3-8b-g128 -b 32 -l 1000 -f 5 -t 1
model_name: "HandH1998/QQQ-Llama-3-8b-g128"
tasks:
- name: "gsm8k"
metrics:
- name: "exact_match,strict-match"
value: 0.419
- name: "exact_match,flexible-extract"
value: 0.416
limit: 1000
num_fewshot: 5
11 changes: 11 additions & 0 deletions .buildkite/lm-eval-harness/configs/Minitron-4B-Base-FP8.yaml
Original file line number Diff line number Diff line change
@@ -0,0 +1,11 @@
# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-vllm-baseline.sh -m mgoin/Minitron-4B-Base-FP8 -b auto -l 1000 -f 5 -t 1
model_name: "mgoin/Minitron-4B-Base-FP8"
tasks:
- name: "gsm8k"
metrics:
- name: "exact_match,strict-match"
value: 0.233
- name: "exact_match,flexible-extract"
value: 0.236
limit: 1000
num_fewshot: 5
Original file line number Diff line number Diff line change
@@ -0,0 +1,11 @@
# bash ./run-lm-eval-gsm-vllm-baseline.sh -m neuralmagic/Mixtral-8x22B-Instruct-v0.1-FP8-dynamic -b "auto" -l 250 -f 5 -t 8
model_name: "neuralmagic/Mixtral-8x22B-Instruct-v0.1-FP8-dynamic"
tasks:
- name: "gsm8k"
metrics:
- name: "exact_match,strict-match"
value: 0.86
- name: "exact_match,flexible-extract"
value: 0.86
limit: 250
num_fewshot: 5
Original file line number Diff line number Diff line change
@@ -0,0 +1,11 @@
# bash ./run-lm-eval-gsm-vllm-baseline.sh -m neuralmagic/Mixtral-8x7B-Instruct-v0.1-FP8 -b "auto" -l 250 -f 5 -t 4
model_name: "neuralmagic/Mixtral-8x7B-Instruct-v0.1-FP8"
tasks:
- name: "gsm8k"
metrics:
- name: "exact_match,strict-match"
value: 0.624
- name: "exact_match,flexible-extract"
value: 0.624
limit: 250
num_fewshot: 5
11 changes: 11 additions & 0 deletions .buildkite/lm-eval-harness/configs/Mixtral-8x7B-Instruct-v0.1.yaml
Original file line number Diff line number Diff line change
@@ -0,0 +1,11 @@
# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-hf-baseline.sh -m neuralmagic/Mixtral-8x7B-Instruct-v0.1 -b 32 -l 250 -f 5 -t 4
model_name: "mistralai/Mixtral-8x7B-Instruct-v0.1"
tasks:
- name: "gsm8k"
metrics:
- name: "exact_match,strict-match"
value: 0.616
- name: "exact_match,flexible-extract"
value: 0.632
limit: 250
num_fewshot: 5
11 changes: 11 additions & 0 deletions .buildkite/lm-eval-harness/configs/Qwen2-1.5B-Instruct-FP8W8.yaml
Original file line number Diff line number Diff line change
@@ -0,0 +1,11 @@
# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-vllm-baseline.sh -m nm-testing/Qwen2-1.5B-Instruct-FP8W8 -b auto -l 1000 -f 5 -t 1
model_name: "nm-testing/Qwen2-1.5B-Instruct-FP8W8"
tasks:
- name: "gsm8k"
metrics:
- name: "exact_match,strict-match"
value: 0.578
- name: "exact_match,flexible-extract"
value: 0.585
limit: 1000
num_fewshot: 5
Original file line number Diff line number Diff line change
@@ -0,0 +1,11 @@
# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-vllm-baseline.sh -m neuralmagic/Qwen2-1.5B-Instruct-quantized.w8a8 -b "auto" -l 1000 -f 5 -t 1
model_name: "neuralmagic/Qwen2-1.5B-Instruct-quantized.w8a8"
tasks:
- name: "gsm8k"
metrics:
- name: "exact_match,strict-match"
value: 0.593
- name: "exact_match,flexible-extract"
value: 0.588
limit: 1000
num_fewshot: 5
Original file line number Diff line number Diff line change
@@ -0,0 +1,11 @@
# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-vllm-baseline.sh -m nm-testing/Qwen2-1.5B-Instruct-W8A16-Channelwise -b "auto" -l 1000 -f 5 -t 1
model_name: "nm-testing/Qwen2-1.5B-Instruct-W8A16-Channelwise"
tasks:
- name: "gsm8k"
metrics:
- name: "exact_match,strict-match"
value: 0.595
- name: "exact_match,flexible-extract"
value: 0.582
limit: 1000
num_fewshot: 5
11 changes: 11 additions & 0 deletions .buildkite/lm-eval-harness/configs/Qwen2-57B-A14-Instruct.yaml
Original file line number Diff line number Diff line change
@@ -0,0 +1,11 @@
# bash ./run-lm-eval-gsm-vllm-baseline.sh -m Qwen/Qwen2-57B-A14B-Instruct -b "auto" -l 250 -f 5 -t 4
model_name: "Qwen/Qwen2-57B-A14B-Instruct"
tasks:
- name: "gsm8k"
metrics:
- name: "exact_match,strict-match"
value: 0.792
- name: "exact_match,flexible-extract"
value: 0.824
limit: 250
num_fewshot: 5
5 changes: 5 additions & 0 deletions .buildkite/lm-eval-harness/configs/models-large.txt
Original file line number Diff line number Diff line change
@@ -0,0 +1,5 @@
Meta-Llama-3-70B-Instruct-FBGEMM-nonuniform.yaml
Meta-Llama-3-70B-Instruct.yaml
Mixtral-8x7B-Instruct-v0.1.yaml
Qwen2-57B-A14-Instruct.yaml
DeepSeek-V2-Lite-Chat.yaml
9 changes: 9 additions & 0 deletions .buildkite/lm-eval-harness/configs/models-small.txt
Original file line number Diff line number Diff line change
@@ -0,0 +1,9 @@
Meta-Llama-3-8B-Instruct.yaml
Meta-Llama-3-8B-Instruct-FP8-compressed-tensors.yaml
Meta-Llama-3-8B-Instruct-INT8-compressed-tensors.yaml
Meta-Llama-3-8B-Instruct-nonuniform-compressed-tensors.yaml
Meta-Llama-3-8B-Instruct-Channelwise-compressed-tensors.yaml
Minitron-4B-Base-FP8.yaml
Qwen2-1.5B-Instruct-INT8-compressed-tensors.yaml
Qwen2-1.5B-Instruct-FP8W8.yaml
Meta-Llama-3-8B-QQQ.yaml
46 changes: 46 additions & 0 deletions .buildkite/lm-eval-harness/run-lm-eval-gsm-hf-baseline.sh
Original file line number Diff line number Diff line change
@@ -0,0 +1,46 @@
#!/bin/bash
# We can use this script to compute baseline accuracy on GSM for transformers.
#
# 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
}

while getopts "m:b:l:f:" OPT; do
case ${OPT} in
m )
MODEL="$OPTARG"
;;
b )
BATCH_SIZE="$OPTARG"
;;
l )
LIMIT="$OPTARG"
;;
f )
FEWSHOT="$OPTARG"
;;
\? )
usage
exit 1
;;
esac
done

lm_eval --model hf \
--model_args pretrained=$MODEL,parallelize=True \
--tasks gsm8k --num_fewshot $FEWSHOT --limit $LIMIT \
--batch_size $BATCH_SIZE
51 changes: 51 additions & 0 deletions .buildkite/lm-eval-harness/run-lm-eval-gsm-vllm-baseline.sh
Original file line number Diff line number Diff line change
@@ -0,0 +1,51 @@
#!/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 lm-eval==0.4.3

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,distributed_executor_backend="ray",trust_remote_code=true,max_model_len=4096 \
--tasks gsm8k --num_fewshot $FEWSHOT --limit $LIMIT \
--batch_size $BATCH_SIZE
Loading

0 comments on commit 19b1562

Please sign in to comment.