People are talking about the new Llama 3.3 70b release, which has generally better performance than Llama 3.1 (approaching 3.1's 405b performance): https://www.llama.com/docs/model-cards-and-prompt-formats/llama3_3
I've been waiting for an open source TTS model that was actually good enough to capture some of the subtleties of language and synthesize them in a natural-sounding way that makes sense. I think I finally found one that fits the requirements.
I've been working on keeping the OSM tool up to date for OpenWebUI's rapid development pace. And now I've added better-looking citations, with fancy styling. Just a small announcement post!
I've been using Qwen 2.5 Coder
(bartowski/Qwen2.5.1-Coder-7B-Instruct-GGUF) for some time now, and it has
shown significant improvements compared to previous open weights models.
I've seen a few commercial services to help you choose the right frames for you or even make recommendations based on your face and eye shape. Is there anything like that which can be used locally without sending data off to a service that does who knows what with that information?
For about half a year I stuck with using 7B models and got a strong 4 bit quantisation on them, because I had very bad experiences with an old *qwen 0.5B model*.
I'm really curious about which option is more popular. I have found, that format JSON works great even for super small models (e.g. Llama 3.2-1B-Q4 and Qwen-2.5-0.5B-Q4) which is great news for mobile devices!
Humans think about different things and concepts for different periods of time. Saying "and" takes less effort to think of than "telephone", as that is more context sensetive.
Hi! I played around with Command R+ a bit and tried to make it think about what it us about to say before it does something. Nothing g fancy here, just some prompt.
Mistral Small 22B just dropped today and I am blown away by how good it is. I was already impressed with Mistral NeMo 12B’s abilities, so I didn’t know how much better a 22B could be. It passes really tough obscure trivia that NeMo couldn’t, and its reasoning abilities are even more refined.
I just found https://www.arliai.com/ who offer LLM inference for quite cheap. Without rate-limits and unlimited token generation. No-logging policy and they have an OpenAI compatible API.
I’m currently using SuperNormal to taking meeting minutes for all of my Teams, Google Meet, and Zoom conference calls. Is there a workflow for doing this locally with Whisper and some other tools? I haven’t found one yet.
Only recently did I discover the text-to-music AI companies (udio.com, suno.com) and I was surprised about how good the results are. Both are under lawsuit from RIAA.
Trying something new, going to pin this thread as a place for beginners to ask what may or may not be stupid questions, to encourage both the asking and answering.
Hi everybody, I find a huge part of my job is talking to colleagues and clients and at the end of those phone calls, I have to write a summary of what happened, plus any key points that I need to focus on followup.
This is a pretty great 1 hour introduction to AI from Andrej Karpathy. It includes an interesting idea of considering LLMs as a sort of operating system, and runs through some examples of jailbreaks.
Concerns about Leadership: There were internal concerns at OpenAI about Sam Altman’s leadership, focusing on his alleged disregard for ethical considerations and priorities set by the organization.
Not my idea, but thought it would be a fun exercise. I’m way too picky, though, and I need to figure out how to give up on hunting for a better iteration before this absorbs my life.
ChatGPT can now create unique images from a simple conversation—and this new feature is available to Plus and Enterprise users today. Describe your vision, and ChatGPT will bring it to life by providing a selection of visuals for you to refine and iterate upon. You can ask for revisions right in the chat. This is powered by our most capable image model, DALL·E 3.
PieFed
c/localllama
c/fosai
Tiime
Smorty [she/her]
Lemmchen
badcodecat
Smokeydope
c/aistuff
Lumberjacked
Bazsalanszky
Salamander
limerod
ijeff
reactive_recall
c/chatgpt
Nemeski
makingStuffForFun
Alice
thirdBreakfast
