-
Notifications
You must be signed in to change notification settings - Fork 1.1k
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
Add support for ggml models #58
Comments
@hippalectryon-0 I got a basic version of this working last night using the llama-cpp-python server and the OpenAI llm implemented here Unfortunately, most of the really interesting features like the RegexProcessor, Token Healing, etc are only available for transformer based models. It looks like there are two options:
|
Yeah I've been trying the first option for a few hours but as you said it requires quite a bit of code-digging, haven't made much progress. |
I tried the second option to implement my own provider for llama-cpp-python in guidance but haven't got very far. |
I think that this package: https://github.com/marella/ctransformers This also has more than just llama, and supports things like |
It doesn't support llama though, from what's in the readme |
|
Ah yeah, I guess I read this issue as In good news, the creator of Might make sense to have both backends, |
Ok, I got a basic version working with guidance and llama-cpp-python. Will clean it up and test a little bit and then post a link here! |
Here is the fork of guidance with llama-cpp-python support: {
"id": "e1f491f7-7ab8-4dac-8c20-c92b5e7d883d",
"description": "A quick and nimble fighter.",
"name": "Katana",
"age": 26,
"armor": "leather",
"weapon": "sword",
"class": "fighter",
"mantra": "I am the sword of justice.",
"strength": 10,
"items": ["a katana", "a leather jacket", "a backpack", "traveler's rations", "water bottle"]
} |
…r additional models Hi @slundberg and all, first off great work on this project, I'm very excited to see how it develops. As per guidance-ai#58 it would be very useful to be able to extend guidance to support additional LLM models and make use of all of the features. I understand this project is quite new and you probably want to avoid the cost of maintaining N implementations. If it's an acceptable solution, can we export `LLMSession` and `SyncSession` so external projects can add support on their own?
@Maximilian-Winter very impressive thank you! I've created a PR to export the two missing |
@Maximilian-Winter Nice ! How does it handle stop words though ? I don't see where they're forwarded |
@hippalectryon-0 I'm currently make some changes to llama-cpp-python to add logits processors and the stop criteria lists. |
@hippalectryon-0 I have fixed all bug on my side and added all the need things in llama-cpp-python to my fork of it. You will find the fork here: |
@Maximilian-Winter Do you have an example? A sample or a list of dependencies? I tried using your fork (for guidance) but just importing it raises an error. I fixed a few ones on my side but i prefer to ask you as I haven't been able to get it to work for now. |
In the new release, we support llama-cpp models. Sorry it took us so long to get to this! They are great, and very fast. |
Issue: we can't import ggml (ex: llama-cpp) models.
The text was updated successfully, but these errors were encountered: