-
Notifications
You must be signed in to change notification settings - Fork 72
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
LLM-model-switcher #32
Conversation
@@ -83,6 +83,8 @@ def __init__( | |||
max_new_tokens=300, | |||
) | |||
self.llm = OpenAI(model="gpt-3.5-turbo-instruct") |
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.
Lets have llama3 8B as default model
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.
And then for line 80: multimodal model default should be set to Llava or even llava-gradient using ollama with option to change to gpt-4-preview
available_models = tuple(model["name"] for model in models_info["models"]) | ||
|
||
if "llama3:8b" in available_models: | ||
selected_model = st.selectbox( |
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.
Does this link back to self.llm?
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.
available models is grabbing from ollama installed models on current device
so no, not yet
Good stuff here, let me give it a go |
All proposed functionalities are included in PR #36 and in release v0.1.2 |
Got the UI and the function + ollama to switch models
Stuck on writing the actual function:
def setLLM(self, llm): print("Setting LLM...", llm)
But will try again tomorrow
Sending PR if anyone knows how to go about this