Viewing profile — dmezzetti

Very interesting project! Are there benchmarks for the "compatibility mode" or are all the numbers for the Gigatoken API?

The recent abrupt removal of the ability to see who has starred a project isn't a good move. Things like this certainly erode trust. https://github.com/orgs/community/discussions/2…

I agree that Kokoro is a good TTS model. If you're interested in an ONNX version and a permissively licensed TTS Tokenizer, I built a pipeline for that a while back: https://huggin…

100% agree on this. I've been working on small local models for years with txtai ( https://github.com/neuml/txtai ). I've published close to 100 models that can run local for RAG, …

Interesting project. Happy to see someone who shares an interest in tiny vector embeddings models. I've worked on tiny (1MB - 4MB, 250K - 950K parameters) embeddings models called …

Why does HN let OpenAI and Anthropic basically advertise but it throws down the gauntlet at a small developer like myself when we do "self promotion"? Top 3 posts as of this moment…

Local models are great for a lot of things past just software development. We need to move towards solving other real world problems vs just building software. I've been focused on…

Well-Read Students Learn Better: On the Importance of Pre-training Compact Models Related paper that's a good read: https://arxiv.org/abs/1908.08962

They have paid hosting - https://huggingface.co/enterprise and paid accounts. Also consulting services. Seems like a pretty good foundation to me.

This is really great news. I've been one of the strongest supporters of local AI dedicating thousands of hours towards building a framework to enable it. I'm looking forward to see…

Why keep relying on API services? If you'd like your own local AI integration with open providers like Rocket.Chat and Mattermost, check out txtchat ( https://github.com/neuml/txtc…

Very interesting! It would be great to see how it compares to Faiss / HNSWLib etc. I'd will consider integrating it into txtai as an ANN backend.

Have you considered using something like claude code / opencode?

It's been an issue for a while and it's even bigger now in the age of AI. Lots of people use security as a way to "have their moment" and don't really care about adding value. But …

It's too bad that Anthropic is so hostile to open source. It's a big missed opportunity for them.

Nice application, great work!

AI Development is good for those who want to do it. But not a terminal career decision for those who don't.

Two words: Open Source.

This change was happening well before LLMs. People were tired of being yelled at and treated poorly. A cautionary tale for many of these types of tech platforms, this one included.…

The message here is good. I've now spent over 5 years in the OSS world ( https://github.com/neuml ). I started by picking a problem I was interested in and checking the work into G…

I love this feature. I've long used json_extract to create dynamic columns with txtai sql: https://neuml.github.io/txtai/embeddings/query/#dynamic-colu... You can do the same with …