Skip to content
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

Merged
merged 5 commits into from
Mar 20, 2024

Conversation

lh0x00
Copy link
Contributor

@lh0x00 lh0x00 commented Mar 14, 2024

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 !

@lh0x00 lh0x00 changed the title Support Ghost 7B v0.9.1, fast, powerful and smooth for Vietnamese and… Support Ghost 7B v0.9.1 gguf Mar 14, 2024
@cebtenzzre
Copy link
Member

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.

@lh0x00 lh0x00 force-pushed the feature/SupportGhost7B-v0.9.1 branch 2 times, most recently from 29d77df to ec0a169 Compare March 14, 2024 17:24
@lh0x00
Copy link
Contributor Author

lh0x00 commented Mar 14, 2024

@cebtenzzre I was negligent in not admitting that early, glad to remind me. I have updated it again, thank you.

gpt4all-chat/metadata/models2.json Outdated Show resolved Hide resolved
@lh0x00 lh0x00 force-pushed the feature/SupportGhost7B-v0.9.1 branch 3 times, most recently from 378932b to cea4172 Compare March 17, 2024 13:07
@lh0x00 lh0x00 requested a review from manyoso March 19, 2024 06:55
"order": "g",
"md5sum": "31b47b4e8c1816b62684ac3ca373f9e1",
"name": "Ghost 7B v0.9.1",
"filename": "model.Q4_0.gguf",
Copy link
Collaborator

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?

Copy link
Collaborator

@manyoso manyoso left a 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>
@lh0x00 lh0x00 force-pushed the feature/SupportGhost7B-v0.9.1 branch from 783e533 to 127f6b2 Compare March 19, 2024 17:32
@lh0x00
Copy link
Contributor Author

lh0x00 commented Mar 19, 2024

hi @manyoso , I am done.

@lh0x00 lh0x00 requested a review from manyoso March 19, 2024 17:37
@manyoso manyoso merged commit 271e6a5 into nomic-ai:main Mar 20, 2024
1 check passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

3 participants