1EvilSexyGenius

joined 1 year ago
sorted by: new top controversial old
When OpenAI takes neutering to the extreme... in c/localllama@poweruser.forum
[โ€“] 1EvilSexyGenius@alien.top 1 points 1 year ago

Wow ๐Ÿคฏ

They're warning the world about the dangers of AI when they're the only ones who seem to have control of it. Who knows wtf they've created behind the scenes and has told no one! We won't find out until there's a news report about their super intelligent being escaping their confines

How much have chatbots like ChatGPT replaced Google or other search engines for you? in c/localllama@poweruser.forum
[โ€“] 1EvilSexyGenius@alien.top 1 points 1 year ago

2% - I don't use chatbots as a replacement for searching and reading for myself. Not yet anyway.

But for abstract thinking, I turn to ai.

For instance, merging two different types of technologies in new ways.

Ai chatbots are good at this

Dolphin or Mistral function calling in c/localllama@poweruser.forum
[โ€“] 1EvilSexyGenius@alien.top 1 points 1 year ago

Not a bad idea but I'm not coding in Python.

Because I hate myself, I'm writing in C# ๐Ÿซ 

Also, I want to use a few libraries as possible.

As a last resort I may use langchain. Or just look at the source and see how they force a model into function calling if it's possible.

Dolphin or Mistral function calling in c/localllama@poweruser.forum
[โ€“] 1EvilSexyGenius@alien.top 1 points 1 year ago

Yes good call ๐Ÿ‘ I'm gonna try that now.

I'm gonna add a system message to the chat history part of the prompt saying that the command is invalid and see if it corrects itself in the next iteration of the loop.

This could add a bandage ๐Ÿฉน on the issue for now. Allowing it to seemlessly loop until a task is complete. Until I can find a better prompt or model.

So far, dolphin-mistral 2.1 7b is what I'm using ATM.

1
Dolphin or Mistral function calling (alien.top)
 

So Im looking for references on how to do function calling using Dolphin or Mistral models.

With my current prompt, I'm able to get it to choose an appropriate command for the task sometimes. But often it'll add multiple commands in one response. But the other half of the time it produces correct commands & parameters in json format as request. Sometimes it makes up commands it want to use that doesn't exist in the command list.

I'm just looking for hints at a more concrete prompt that will make these models effective in function calling.

Should I try whatever format OpenAI use seeing as how these smaller models are usually trained on synthetic data produced by OpenAI models?

Any guidance is appreciated ๐Ÿ‘