e489ad7a21
- **Add SPDX license headers to python source files**
- **Check for SPDX headers using pre-commit**
commit 9d7ef44c3cfb72ca4c32e1c677d99259d10d4745
Author: Russell Bryant <rbryant@redhat.com>
Date: Fri Jan 31 14:18:24 2025 -0500
Add SPDX license headers to python source files
This commit adds SPDX license headers to python source files as
recommended to
the project by the Linux Foundation. These headers provide a concise way
that is
both human and machine readable for communicating license information
for each
source file. It helps avoid any ambiguity about the license of the code
and can
also be easily used by tools to help manage license compliance.
The Linux Foundation runs license scans against the codebase to help
ensure
we are in compliance with the licenses of the code we use, including
dependencies. Having these headers in place helps that tool do its job.
More information can be found on the SPDX site:
- https://spdx.dev/learn/handling-license-info/
Signed-off-by: Russell Bryant <rbryant@redhat.com>
commit 5a1cf1cb3b80759131c73f6a9dddebccac039dea
Author: Russell Bryant <rbryant@redhat.com>
Date: Fri Jan 31 14:36:32 2025 -0500
Check for SPDX headers using pre-commit
Signed-off-by: Russell Bryant <rbryant@redhat.com>
---------
Signed-off-by: Russell Bryant <rbryant@redhat.com>
67 lines
1.8 KiB
Python
67 lines
1.8 KiB
Python
# SPDX-License-Identifier: Apache-2.0
|
|
|
|
import openai # use the official client for correctness check
|
|
import pytest
|
|
import pytest_asyncio
|
|
# downloading lora to test lora requests
|
|
from huggingface_hub import snapshot_download
|
|
|
|
from ...utils import RemoteOpenAIServer
|
|
|
|
# any model with a chat template should work here
|
|
MODEL_NAME = "HuggingFaceH4/zephyr-7b-beta"
|
|
# technically this needs Mistral-7B-v0.1 as base, but we're not testing
|
|
# generation quality here
|
|
LORA_NAME = "typeof/zephyr-7b-beta-lora"
|
|
|
|
|
|
@pytest.fixture(scope="module")
|
|
def zephyr_lora_files():
|
|
return snapshot_download(repo_id=LORA_NAME)
|
|
|
|
|
|
@pytest.fixture(scope="module")
|
|
def server(zephyr_lora_files):
|
|
args = [
|
|
# use half precision for speed and memory savings in CI environment
|
|
"--dtype",
|
|
"bfloat16",
|
|
"--max-model-len",
|
|
"8192",
|
|
"--enforce-eager",
|
|
# lora config below
|
|
"--enable-lora",
|
|
"--lora-modules",
|
|
f"zephyr-lora={zephyr_lora_files}",
|
|
f"zephyr-lora2={zephyr_lora_files}",
|
|
"--max-lora-rank",
|
|
"64",
|
|
"--max-cpu-loras",
|
|
"2",
|
|
"--max-num-seqs",
|
|
"128",
|
|
]
|
|
|
|
with RemoteOpenAIServer(MODEL_NAME, args) as remote_server:
|
|
yield remote_server
|
|
|
|
|
|
@pytest_asyncio.fixture
|
|
async def client(server):
|
|
async with server.get_async_client() as async_client:
|
|
yield async_client
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_check_models(client: openai.AsyncOpenAI, zephyr_lora_files):
|
|
models = await client.models.list()
|
|
models = models.data
|
|
served_model = models[0]
|
|
lora_models = models[1:]
|
|
assert served_model.id == MODEL_NAME
|
|
assert served_model.root == MODEL_NAME
|
|
assert all(lora_model.root == zephyr_lora_files
|
|
for lora_model in lora_models)
|
|
assert lora_models[0].id == "zephyr-lora"
|
|
assert lora_models[1].id == "zephyr-lora2"
|