On: llama.cpp

[halyconWays]

llama.cpp is like the ffmepg of AI, and one of the reasons I so greatly dislike ollama is that the latter completely obfuscates that they're a rebrand of the former. Georgi Gerganov and team did all the hard work; ollama is langchain-like VC-bait with a HF download wrapper.

[woadwarrior01 → halyconWays]

ICYMI, llama.cpp was also VC funded. Search for "ggml" on this page:

https://aigrant.com

[kennywinker → halyconWays]

llama.cpp will happily download models from hugging face, btw.

[woadwarrior01 → kennywinker]

Huggingface now owns llama.cpp, btw.

https://huggingface.co/blog/ggml-joins-hf