-
Notifications
You must be signed in to change notification settings - Fork 30.9k
deci gguf support #38669
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
deci gguf support #38669
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM thanks for adding this 🔥 ! can you please add some tests in tests/quantization/ggml/ ?
tests/quantization/ggml/test_ggml.py
Outdated
| try: | ||
| original_model = AutoModelForCausalLM.from_pretrained( | ||
| original_model_id, | ||
| torch_dtype=torch.float16, | ||
| trust_remote_code=True, | ||
| device_map="auto", | ||
| ) | ||
| except Exception as e: | ||
| self.skipTest(f"Original Deci model not available for comparison: {e}") | ||
| return |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Why do we need this try: ... excetpt: .... statement in test? Should't the test failed if it encounter an Exception?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Can you address this too?
|
hey , any update on this ? |
I think after resolving conflicts we're good to go? Looking forward to this pr! Thanks. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Sorry for missing this thread! LGTM
tests/quantization/ggml/test_ggml.py
Outdated
| try: | ||
| original_model = AutoModelForCausalLM.from_pretrained( | ||
| original_model_id, | ||
| torch_dtype=torch.float16, | ||
| trust_remote_code=True, | ||
| device_map="auto", | ||
| ) | ||
| except Exception as e: | ||
| self.skipTest(f"Original Deci model not available for comparison: {e}") | ||
| return |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Can you address this too?
|
thanks for keeping up with the pr ❤️ |
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM !
|
[For maintainers] Suggested jobs to run (before merge) run-slow: ggml |
What does this PR do?
GGUF support for deci
Fixes #37736
Before submitting
Who can review?
@MekkCyber