I use chat.petals.dev I think that is also open source

Also want to mention privateGPT

.

I’ve been using iask.ai or Phind.com for mostly quick answers to my simple questions, these get me by but I’m no coder or author and I have noticed these options are often pretty terrible for math queries.

Edit: the above services I’m pretty sure are not open source, but their privacy policies seem reasonable.

Holy Cyberjesus… I don’t experience with ChatGPT and the likes, and it’s obviously only one response, but the answer I got from api.together.xy to “Is it okay to do intense tempo runs in winter?” is absolutely useless and wrong and neglecting the actual problems that are usually mentioned (cold air while breathing intensely):

Intense tempo runs are usually done at tempo, which means that your foot contacts the ground after a relatively long time. This is different from the typical duration of a foot contact in normal running. In normal running, the foot contacts the ground after a relatively short time. In a tempo run, the duration of your foot contact with the ground is increased, which causes you to run at a faster pace than usual.

Intense tempo runs are typically done in the winter, when the ground is harder and more difficult to run on. Hard ground can be more damaging to your body, so it’s important to be careful when running on snow, ice, or concrete. It’s important to take safety precautions when doing intense tempo runs in the winter, such as wearing proper shoes and clothing, and avoiding running on icy or snowy surfaces.

It’s important to note that intense tempo runs can be dangerous if not done properly. It’s important to have a good understanding of your body and what works best for you. It’s also important to consult with a doctor before starting any new running program, especially if you have any previous injuries or health concerns.

No mention of the ai horde , seriously? We have thousands of users!

As it’s to be expected from this website, the article quality is subpar.

They mix third party hosted LLMs, with frontends (KoboldAI, GPT4ALL) and with local models (which BTW, every single one of them is a llama finetune. They’ve never heard of mistral or others, apparently).

If I hadn’t read this website years ago and knew that the quality was already trash back then, I’d say this very article was written by a LLM.

It’s a bad list.

YSK: There are several things mixed in it.

1. There are “models” (usually meaning “weights” specifically). The models (weights) are the raw data that contain the wisdom of the AIs.
2. There is software to “run” these models on your own machine, or to connect to an API.
3. There are services which run models for you and let you interact via web interface, app, or API. Some services may add text to your prompt, to create a better(?) prompt.

There is a bewildering array of models out there. Mostly, they are specialized and/or merged versions of some popular foundation models (by mistral, meta, and a few others). Without endorsing any service, I find that openrouter.ai and together.ai let you try a fairly large selection. There are other services.

You can find more/better information here: !localllama@sh.itjust.works

Very strange article. It lists several front ends, some of which are not open source, as well as some raw models without clearly distinguishing between them. RWKV was mentioned which is cool I guess.

The first option listed should have been huggingchat, followed by the various local UIs, with a separate section discussing the models themselves.

Pretty bad article, but here are my two cents on the actual answer, as of right now:

• General chatting: OpenHermes
• General querying, instruction: Mistral
• Coding: Deepseek-coder

These perform similar to or better than ChatGPT 3.5, in some cases comparable to 4.

For specific niche applications (role playing, nsfw stories, etc), just search on huggingface.co and read the user reviews.