Christian Weyer

Issue on Windows

1

Issue on Windows: --- python nw_package_tool.py --all ngmd Begin to compress app. Compressing app ends. Get newest stable version Download node-webkit binary Traceback (most recent call last): File "nw_package_tool.py", line...

feat: Apple M1/M2 support through MPS

1

### Feature request I want to use OpenLLM with available models to run on Apple M1/M2 processors (GPU support) through MPS. Today: ``` openllm start falcon No GPU available, therefore...

feat: Support Function Calling in llama3.1

6

## Goal - llama3.1 should support Tool use in llama.cpp - https://github.com/janhq/models/issues/16 ## Original post **Problem** AFAICS, the current implementation does not have OpenAI Function Calling support. This would be...

Agent output streams

6

I just saw that AutoGen is planning to add an output streams feature beyond console output. https://github.com/microsoft/autogen/pull/1290#discussion_r1460794605 This would be great if crewAI would provide a similar feature.

https://huggingface.co/papers/2402.01622

Wrong target host is used although raw HTTP request shows the right target host

12

## Description This is really strange. I am using Proxyman on macOS all the time without any issues. Now, I have a node.js app that uses axios to talk to...

Fixing Open AI tool calling result syntax for Ollama models

3

See https://github.com/BerriAI/litellm/issues/2209#issuecomment-2007993125

How could an LLM-based OS become reality in the light of non-determinism & hallucination?

2

I love the idea!!! But... how could an LLM-based OS become reality in the light of non-determinism & hallucination?

Submit tests to GAIA benchmark

2

GAIA is a benchmark which aims at evaluating next-generation LLMs (LLMs with augmented capabilities due to added tooling, efficient prompting, access to search, etc). Paper: https://arxiv.org/abs/2311.12983 > We introduce GAIA,...

:-) https://github.com/microsoft/autogen https://microsoft.github.io/autogen/