There’s lots of ways to skin this particular cat. My current approach is low powered Synology (j series?) for mass storage, then 1 litre PC’s running proxmox for my compute power using their NVME for storage, all backed up to the Synology.
Two good points here OP. Type docker image ls to see all the images you currently have locally - you’ll possibly be surprised how many. All the ones tagged <none> are old versions.
If you’re already using github, it includes an package repository you could push retagged images to, or for more self-hosty, a local instance of Forgejo would be a good option.
Build anything small into a container on your laptop, push it to DockerHub or the Github package registry then host it on fly.io for free.
Great write up, thanks. For video learners, Wolfgang does a good step-by-step on YouTube
I’d love you to check back later with your conclusions.
Guide to Self Hosting LLMs with Ollama.
ollama run llama3.2If it’s an M1, you def can and it will work great. With Ollama.
+1 for Forgejo. I started on Gogs, then gathered that there had been some drama with that and Gitea. Forgejo is FOSS, simple to get going, and comfortable to use if you’re coming from GitHub. It’s actively maintained, and communication with the project is great.
Great question (and we are reaching the outside edge of my knowledge here). Something like 3-5% of carbon in plants is taken up from the soil by plant roots. I don’t fully understand the mechanism, but the organic carbon percentage is an important competent in the calculation of how much artificial nitrogen a crop is going to need, so I guess it’s probably some biochemical process for making the nitrogen available.
The organic carbon percentage is closely watched by farmers and is something of an indication of soil health. ie if your crop rotation is reducing the OC% over time then you probably need to reconsider it. It’s one of the reasons burning crop stubbles is a much rarer practice now.
Hay is cut from any sort of cereal plant early in it’s lifecycle, specifically before the plant starts concentrating it’s energy into the seeds. At this stage the plant stalk is sweeter (even to a human - give it a bite). After flowering, the plant is concentrating it’s energy into the seeds. By the time it’s fully done this (which takes a number of weeks), there is very little protein in the stalk, and it’s far less palatable (or nutritious) to animals. The plant stalk is now essentially ‘straw’.
Commercial hay can be mowed from a meadow (in Australia usually ryegrass) in which case it will have all sorts mixed in, or from crops intended for making good hay (in Australia usually oats or wheat). Commercial straw (which has a tiny market) is cut after the grain has been harvested from the top of the plant. In commercial broadacre cropping in poor soil areas (the bulk of Australia’s grain areas) it’s usually better economics to keep your crop residue including straw since the cost to replace the carbon would be higher that what you’d get for the straw after the cost of harvesting it.
Source: I play a lot of Minecraft
Thanks, I ended up going with Garage, but it has the same issue. I assumed I could just specify some buckets with their keys in the docker-compose or garage.toml, but no - they had to be done through the api or command line.
This is correct, I already installed the minio cli, but when I came back and read this, I tried it out and yes, once garage is running in the container, you can
alias garage="docker exec -ti <container name> /garage"
so you can do the cli things like garage bucket info test-bucket or whatever. The --help for the garage command is pretty great, which is good since they don’t write it up much in the docs.
Thanks. I ended up going with Garage (in Docker), and installed the minio client cli for these tasks.
One I’m writing. I use the host file system (as I have a strong preference for simple) for it’s storage, but I’m interested in adding Litestream for replicating the database onto AWS.
"Convert this text to make it sound like from a random person: "
Love the effort you’ve put into this question. You’ve clearly done some quality research and thinking.
When I asked myself this same question a couple of years ago, I ended up just buying a second hand Synology NAS to use alongside my mini-pc. That would meet your criteria, and avoids the (I’m not sure what magnitude) reliability risk of using disks connected over USB. It’s more proprietary than I’d like, but it’s battle tested and reliable for me.
starcoder2:latest f67ae0f64584 1.7 GB 3 days ago
phi3:latest d184c916657e 2.2 GB 3 weeks ago
deepseek-coder-v2:latest 8577f96d693e 8.9 GB 3 weeks ago
llama3:8b-instruct-q8_0 1b8e49cece7f 8.5 GB 3 weeks ago
dolphin-mistral:latest 5dc8c5a2be65 4.1 GB 3 weeks ago
codeqwen:latest df352abf55b1 4.2 GB 3 weeks ago
llama3:latest 365c0bd3c000 4.7 GB 4 weeks ago
I mostly use starcoder2 with Continue for code autocomplete, the big deepseek coder is a bit slow (I can feel it thinking), but it and the regular llama3 are good for chatbot type programming questions.
I don’t really have anything to compare the M1 performance to. I guess the 8GB models output text a little slower than the web versions of the same models, and the 4GB ones about the same. Using ollama in the terminal, there’s sometimes a 0.5-2 second pause before it starts outputting. Not with phi3 though - it’s surprisingly snappy for the quality of answers.
An M1 MacBook with 16GB cheerfully runs llama3:8b outputting about 5 words a second. A second hand MacBook like that probably costs half to a third of a secondhand RTX3090.
It must suck to be a bargain hunting gamer. First bitcoin, and now AI.
edit: a letter
I use the Continue VS Code plugin with Ollama to use a couple of different models (deepseek-coder-v2 & starcoder2) to recreate a local only Github Copilot type experience for coding. This is on an M1 Apple Silicon though. For autocomplete the generation needs to be pretty brisk - I’m not sure how that would go in a VM without a GPU.
+1 for the Seiko 5s. Love me a SNZG07J1