-
Notifications
You must be signed in to change notification settings - Fork 7.6k
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
Support Ghost 7B v0.9.1 gguf #2127
Conversation
Is this a Q4_0 model, or a Q4_K_M model? Q4_0 models are best because they can be GPU accelerated on Windows and Linux in the current version of GPT4All. Also, you'll need to sign off on your commits for this PR to be accepted. |
29d77df
to
ec0a169
Compare
@cebtenzzre I was negligent in not admitting that early, glad to remind me. I have updated it again, thank you. |
378932b
to
cea4172
Compare
gpt4all-chat/metadata/models2.json
Outdated
"order": "g", | ||
"md5sum": "31b47b4e8c1816b62684ac3ca373f9e1", | ||
"name": "Ghost 7B v0.9.1", | ||
"filename": "model.Q4_0.gguf", |
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 please rename this filename to something more descriptive?
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.
This is targeting models2.json when it should be targeting models3.json as that is our current live model file.
… English languages. Signed-off-by: Lam Hieu <lamhieu.vk@gmail.com>
Signed-off-by: Lam Hieu <lamhieu.vk@gmail.com>
Signed-off-by: Lam Hieu <lamhieu.vk@gmail.com>
Signed-off-by: Lam Hieu <lamhieu.vk@gmail.com>
Signed-off-by: Lam Hieu <lamhieu.vk@gmail.com>
783e533
to
127f6b2
Compare
hi @manyoso , I am done. |
I have added the Ghost 7B v0.9.1 model to the support list.
Nice to see it will be merged and officially used soon.
Model at HuggingFace:
Thanks for review !