-
Notifications
You must be signed in to change notification settings - Fork 274
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
local-apps: update llama.cpp snippet #1103
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.
very neat, UX is much better!
Will update the docs in a sec to reflect the same |
Let's merge this @Vaibhavs10 ? |
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.
@ggerganov tweeted about this new syntax so imo let's go 😁
Ah, apologies if this was too early to showcase! |
not at all! it's great! |
I forgot to rebase with latest `main` to see if the lint passes or not, ref: #1103
This change is related to these upstream PR: - ggerganov/llama.cpp#11195 allows using tag-based repo name like on ollama - ggerganov/llama.cpp#11214 automatically turn on `--conversation` mode for models having chat template Example: ```sh # for "instruct" model, conversation mode is enabled automatically llama-cli -hf bartowski/Llama-3.2-1B-Instruct-GGUF # for non-instruct model, it runs as completion llama-cli -hf TheBloke/Llama-2-7B-GGUF -p "Once upon a time," ```
I forgot to rebase with latest `main` to see if the lint passes or not, ref: huggingface#1103
This change is related to these upstream PR:
--conversation
mode for models having chat templateExample: