feat: load model from modelscope #2
Open
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
added 3 commits
February 5, 2025 14:58
suluyana
force-pushed
the
modelscope_patch_hub
branch
from
53308ec to
6bfe5cc
Compare
yingdachen
reviewed
Feb 11, 2025
README.md
Outdated
| ```py | ||
| from gptqmodel import GPTQModel | ||
| # load Qwen/Qwen2-VL-7B-Instruct-GPTQ-Int4 from modelscope | ||
| model = GPTQModel.load("Qwen/Qwen2-VL-7B-Instruct-GPTQ-Int4") |
There was a problem hiding this comment.
result = model.generate("Uncovering deep insights begins with")[0]
也加上
tests/test_modelscope.py
Outdated
| import importlib.util # noqa: E402 | ||
|
|
||
| if importlib.util.find_spec("modelscope") is None: | ||
| subprocess.check_call([sys.executable, "-m", "pip", "install", "modelscope>=1.23"]) |
added 2 commits
February 17, 2025 15:04
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Hello,
First of all, thank you very much for your group's high-quality open-source LLM model compression/quantization toolkit. In this pull request, I have added an environment variable called "GPTQMODEL_USE_MODELSCOPE". With this environment variable, Chinese users can directly retrieve models from ModelScope, which is significantly faster.
ModelScope is the largest model community in China. It serves as a premier platform designed to bridge model checkpoints with model applications, offering the essential infrastructure to facilitate the sharing of open models and promote model-centric development. For more information, visit our GitHub page: ModelScope.