732851f105
* restore to current phi modeling code from phi-2 * enable gradient checkpointing * don't cast everything to float32 all the time * gradient checkpointing for phi2 ParallelBlock module too * fix enabling flash attn for phi2 * add comment about import * fix phi2 example * fix model type check for tokenizer * revert float32 -> bf16 casting changes * support fused dense flash attn * fix the repo for flash-attn * add package name for subdir pkg * fix the data collator when not using sample packing * install packaging for pytests in ci * also fix setup to not install flash attn fused dense subdir if not extras * split out the fused-dense-lib in extra requires * don't train w group_by_length for phi * update integration test to use phi2 * set max steps and save steps for phi e2e tests * try to workaround ssave issue in ci * skip phi2 e2e test for now
66 lines
2.0 KiB
Python
66 lines
2.0 KiB
Python
"""setup.py for axolotl"""
|
|
|
|
from importlib.metadata import PackageNotFoundError, version
|
|
|
|
from setuptools import find_packages, setup
|
|
|
|
|
|
def parse_requirements():
|
|
_install_requires = []
|
|
_dependency_links = []
|
|
with open("./requirements.txt", encoding="utf-8") as requirements_file:
|
|
lines = [r.strip() for r in requirements_file.readlines()]
|
|
for line in lines:
|
|
if line.startswith("--extra-index-url"):
|
|
# Handle custom index URLs
|
|
_, url = line.split()
|
|
_dependency_links.append(url)
|
|
elif (
|
|
"flash-attn" not in line
|
|
and "flash-attention" not in line
|
|
and "deepspeed" not in line
|
|
and line
|
|
and line[0] != "#"
|
|
):
|
|
# Handle standard packages
|
|
_install_requires.append(line)
|
|
|
|
try:
|
|
torch_version = version("torch")
|
|
if torch_version.startswith("2.1.1"):
|
|
_install_requires.pop(_install_requires.index("xformers==0.0.22"))
|
|
_install_requires.append("xformers==0.0.23")
|
|
except PackageNotFoundError:
|
|
pass
|
|
|
|
return _install_requires, _dependency_links
|
|
|
|
|
|
install_requires, dependency_links = parse_requirements()
|
|
|
|
|
|
setup(
|
|
name="axolotl",
|
|
version="0.3.0",
|
|
description="LLM Trainer",
|
|
long_description="Axolotl is a tool designed to streamline the fine-tuning of various AI models, offering support for multiple configurations and architectures.",
|
|
package_dir={"": "src"},
|
|
packages=find_packages(),
|
|
install_requires=install_requires,
|
|
dependency_links=dependency_links,
|
|
extras_require={
|
|
"flash-attn": [
|
|
"flash-attn==2.3.3",
|
|
],
|
|
"fused-dense-lib": [
|
|
"fused-dense-lib @ git+https://github.com/Dao-AILab/flash-attention@v2.3.3#subdirectory=csrc/fused_dense_lib",
|
|
],
|
|
"deepspeed": [
|
|
"deepspeed",
|
|
],
|
|
"mamba-ssm": [
|
|
"mamba-ssm==1.0.1",
|
|
],
|
|
},
|
|
)
|