-
-
Notifications
You must be signed in to change notification settings - Fork 1.8k
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
TheBloke's future models won't work with LocalAI #1163
Comments
not really, LocalAI supports (thanks to the @dave-gray101 contribution ) chat message template. this doesn't look like much different from llama2 and can be accomplished among the lines. See also the model gallery with a template example: https://github.com/go-skynet/model-gallery/blob/main/llama2-7b-chat-gguf.yaml |
So we can build a ChatML template that will work with OpenAI's Chat Markup Language (ChatML) format, with <|im_start|> and <|im_end|> tokens? |
yes definetly! |
so if I'm reading correctly a chat template might be look like this, but note, I've didn't tried it yet:
|
GGUF does this auto, it would be use the one on the demo page if using a GGUF model, love the new meta data in the model <3 |
this is just for chat models and not instructors for what I can see - I doubt the prompt is injected inside the model file |
good to know about this, I'm in the process of improving the model gallery scraper right now, and I'll add this to the list of things to test for |
@dave-gray101, another thing to look out for... the last time I checked out the scraper, it seemed to be downloading *.bin files only, however TheBloke has switched to *.gguf files. In my own gallery scraper I added support for both and found an extra 400+ new models from TheBloke 😅 |
ggml seems deprecated on TheBloke models , (https://huggingface.co/TheBloke/CodeLlama-13B-Instruct-GGML) |
|
Having found models from TheBloke to be particular well documented and easy to work with, I have basically stopped looking at any other. I even built my own TheBloke filtered gallery.
This seemed to work well, for a while at least. However, The Bloke recently switched to using ChatML for all future models.
See here:
https://www.google.com/search?hl=en&q=%22All%20of%20my%20future%20models%20will%20use%20ChatML%20prompt%20format%22
"All of my future models will use ChatML prompt format" - TheBloke
...
Originally posted by @no-skynet in #67 (comment)
The text was updated successfully, but these errors were encountered: