How is that a “regime position”?

You are only saying this because you agree with general regime positions…

Please name 2.

Censorship and bias is nowhere near as bad in Chinese model. Try even a local Deepseek model and you’ll see it.

It would work the same way, you would just need to connect with your local model. For example, change the code to find the embeddings with your local model, and store that in Milvus. After that, do the inference calling your local model.

I’ve not used inference with local API, can’t help with that, but for embeddings, I used this model and it worked quite fast, plus was a top2 model in Hugging Face. Leaderboard. Model.

I didn’t do any training, just simple embed+interference.

Milvus documentation has a nice example: link. After this, you just need to use a persistent Milvus DB, instead of the ephimeral one in the documentation.

Let me know if you have further questions.

OP can also use an embedding model and work with vectorial databases for the RAG.

I use Milvus (vector DB engine; open source, can be self hosted) and OpenAI’s text-embedding-small-3 for the embedding (extreeeemely cheap). There’s also some very good open weights embed modelsln HuggingFace.

Same thing in Colombia. Something I really like about living here.

I manage some servers and awk can be useful to filter data. If you use commands like grep, and use the pipe operator (the " | " command), awk can be very handy.

Sure, a Python script can do that as well, but doing a one-liner in Bash is waaay faster to program.

Thanks!

If you don’t mind connecting directly with your IP address, you don’t even have to pay a domain. Been doing this for around 2 years

No direct answer here, but my tests with models from HuggingFace measured about 1.25GB of VRAM per 1B parameters.

Your GPU should be fine if you want to play around.

Agree, but that’s reality. People suck, world sucks, life sucks.

You don’t have to change your lifestyle over whatever thing that <random person you don’t know nor care about> decided to say today. It is not wrong to feel that way neither. But, IMO, being aware of that, or at least being open to learn about that stuff, helps a lot to being in peace with it, and eventually, could lead to a more ethical consumption without going to extremes.

It has always been. FOSS is by itself political, just beyond the basic binary logic of left/right.

Your apoliticism is a political instance as well. Take for instance this quoute from Desmond Tutu “If you are neutral in situations of injustice, you have chosen the side of the oppressor.”

I’m not saying you have to ditch Proton over their CEO’s takes, my point is that thinking that everything suddenly became political is naive.

For the media server, I recommend taking a look at Jellifyn. If you want some fancy statistics use, also give it a look at a Prometheus+Graphana config.

Based on your comment, I understand that AMD GPUs aren’t capable of 8k@60 over HDMI. Is that the case? If so, why?

Do you know how can I migrate my Firefox data to Librewolf? I think my main concern is history and then open tabs.

La cantidad de latinos es muy baja u.u

La cantidad de latinos es muy baja u.u

Do you get a tracker-free software version, or just an ad-free experience?

The torrent protocol works by having uploader (seeders) users sharing their files to downloader users (leechers). Users are topically both seeders and leechers.

With that in mind, to seed a file means to share it with others. And yes, you need your torrent client open for that. QBitTorrent is amazing and doesn’t have much overhead in your system, plus you can limit your upload speed and net upload. Some console-based torrent apps are even lighter. No VPS required unless you have specific constraints.