walking-octopus

- GPT-2 and GPT-J usage is [outlined in the README](https://github.com/ggerganov/ggml#gpt-inference-example). - T5 inference is being worked on in PR #12.

Duplicate of #4.

I think it is relevant that in #43 @skeskinen had implemented [bert.cpp](https://github.com/skeskinen/bert.cpp).

Thank you for the timely response. I'd be interested to see how well the 13B model performed on these questions, which I can't do since I only have 8GB of...

The newly released WizardLM 13B, which dataset included more physics questions, had finally started forming coherent reasoning chains, correctly doing basic calculations, rearranging equations, and solves simple problems as well...

Had there been any progress on this? Mitigating hallucinations could be one of the most important obstacles to mass local LLM adoption. If this is any better than RLHF or...

Bark is rather unstable, slow, and overkill for an assistant. [Piper](https://github.com/rhasspy/piper) however seems fine. It also has [Python support](https://github.com/rhasspy/piper#running-in-python). I also wonder if the server or client should be responsible...

Perhaps something like Toolformer, with special tokens for intermediate tool use and its output, may be feasible.

Update: The issue resolved on its own. However, after reading the log provided, I see no mention of `miio-yeelink` integration. It just talks about some boiler or something... Can anyone...

> Whoops, you're right, I thought Mimic was an STT engine instead — my bad. But it sounds like I was understood nevertheless. :) > > You're right that Raspberry...