Skip to content

Commit

Permalink
lcpp docs
Browse files Browse the repository at this point in the history
  • Loading branch information
danemadsen committed Jul 9, 2024
1 parent ad4584f commit a3f9f08
Showing 1 changed file with 12 additions and 1 deletion.
13 changes: 12 additions & 1 deletion docs/README.md
Original file line number Diff line number Diff line change
@@ -1,4 +1,6 @@
# Supported API's
# Large Language Model API's

## Supported API's

| Parameter | Llama.cpp | Ollama | OpenAI | MistralAI | Gemini |
| ----------------------- | --------- | ------ | ------ | --------- | ------ |
Expand Down Expand Up @@ -44,3 +46,12 @@
| Function Call | No | No | Yes | No | No |
| User | No | No | Yes | No | No |
| Safe Mode | No | No | No | Yes | No |

## Llama.CPP

1. On the main page ensure the LlamaCPP option is selected in the API dropdown.
2. Press the menu button on the top right and select `Model Settings` option.
3. Press the `Load Model` button to load a `GGUF` model from local storage. *
4. Navigate back to the main page and initiate a conversation.

* Alternatively you can press the `Huggingface` button to the left of the `Load Model` button to download a model directly from the internet.

0 comments on commit a3f9f08

Please sign in to comment.