No, sorry, that’s the file extension. For example, this page has some large *.gguf files split into parts (because Hugging Face has a max upload size of 50GB): https://huggingface.co/mradermacher/dolphin-2.9.2-mixtral-8x22b-GGUF
Once you download the two parts, you can combine them into the single *.gguf file that ollama is able to import. Instructions for combining the part files can be found here: https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF
Ah but it does! Once you download the gguf file from Hugging Face, you can use ollama’s create command, passing in a Modelfile that specifies the path the the gguf. Then you can use ollama run to start up the model.
It’s kinda annoying but there are instructions online: https://www.markhneedham.com/blog/2023/10/18/ollama-hugging-face-gguf-models/
I used this technique to run mradermacher/dolphin-2.9.2-mixtral-8x22b-GGUF: https://huggingface.co/mradermacher/dolphin-2.9.2-mixtral-8x22b-GGUF
Learning more about running my own LLM models at home. Apparently, the quantization method impacts performance differently on different kinds of hardware.
This is why, if you’re browsing models on Hugging Face, you’ll see files with suffixes like “Q3_K_S” and “IQ2_XXS”. The number after the “Q” tells you which quantization method the model uses. Some will be much slower than others depending on the capabilities of the CPU and GPU in the machine. #llm
Imagine being a government, having stumbled on some #Bitcoin and then SELLING it for THE VERY CURRENCY YOU ALONE CAN PRINT.
We are fortunate to have such dumbass adversaries.
Yes, still. It’s too useful a technology to be abandoned.
It would be clever to show green even when muted to trick the candidate into speaking into dead air and looking like an ass hat.
Not that anyone would be motivated by such thoughts.
Gotta play the game you’re in.
Cacheing. Wish the app would cache old messages so that when it starts up it can show something immediately, rather than waiting for notes from relays.
It’s true. No tiers in this system.
anemoia.
anemoia - n. nostalgia for a time you’ve never known.
https://v.nostr.build/7GjRv.mp4
Imagine stepping through the frame into a sepia-tinted haze, where you could sit on the side of the road and watch the locals passing by. Who lived and died before any of us arrived here, who sleep in some of the same houses we do, who look up at the same moon, who breathe the same air, feel the same blood in their veins—and live in a completely different world.
yt
paranoimia.
paranoimia - n. music video by the Art of Noise featuring Max Headroom
nostr:npub1n0sturny6w9zn2wwexju3m6asu7zh7jnv2jt2kx6tlmfhs7thq0qnflahe
Often when I go to “view” a user’s profile on nostr:npub1n0stur7q092gyverzc2wfc00e8egkrdnnqq3alhv7p072u89m5es5mk6h0 client, I am actually wondering “who is this person in relation to me?”.
What posts of mine has this person interacted with or vice versa?
What other posts have we both commented on or liked?
How do I know this person?
Have they zapped me?
Of course, a users profile view wouldn’t have such an “Interactions” tab available … would it?
That’s a great idea. There are a lot of visualization opportunities
Blows my mind that governments would sell the money that’s strictly finite for the currency they produce in unlimited quantity.
We’re fortunate to have such moronic adversaries.
Good question! I’m not sure, I’ll have to check.
