sroecker
Joined 16 years ago
Karma
56
Submissions
23
Member since
Aug 26
http://twitter.com/sroecker
View on Hacker NewsRecent submissions
Comment · 1 year ago
Yes, but ramalama defaults to podman. Podman Desktop is very easy to install and use.
Comment · 2 years ago
He also built a nice "little" cluster with Nat for their startups: https://andromeda.ai/
Comment · 2 years ago
Yes, used by Grok: https://twitter.com/qdrant_engine/status/1721097971830260030
Oh wow, completely missed that they're German. Should have noticed their "Impressum"..
Comment · 2 years ago
Care to enlighten us why?
Comment · 2 years ago
You probably don't need fine-tuning, at least if it's just new content (and no new instructions). It may even be detrimental, since LLMs are als good at forgetting: https://twitter.com/abacaj/status/1739015011748499772
Comment · 2 years ago
Good question, as you can see I haven't touched it for a month. I wanted to show what's possible then with open source and (open) local models and there's already so much new stuff out there.
I'll probably fix some things this week and then either update it or start from scratch. Guided generation, structured extraction, function calling and multi-modal are things I wanted to add and chainlit looks interesting.
Comment · 2 years ago
We just held a workshop about this a few weeks ago: https://red.ht/llmappdev
We created a simple chatbot using local models with Ollama (llamacpp), LlamaIndex and streamlit.
Have a look at the streamlit folder, it's super easy.
I used this simple example to teach about RAG, the importance of the system prompt and prompt injection. The notebook folder has a few more examples, local models can even do natural language SQL querying now.
Comment · 3 years ago
I can't even see the pay what you like feature on the app.
Comment · 3 years ago
That version of libnc_cuda.so doesn't seem to be compatible with ts_server though.
Comment · 10 years ago
$25B and they can't even afford an API..
If you want analytics you have to rely on a 3rd party provider who somehow gets the information by logging into your account. I guess if you're a key account they will send you some data and maybe even some nice visualizations.
I did some research and people really track their audience with spread sheets. Influencers send screenshots of their accounts to advertisment companies to prove how many followers they have. Seriously.. If they want to monetarize their platform they should open at least part of their API.
Comment · 10 years ago
Please do not use Telegram. It' closed source and uses some half-baked crypto. Signal is open source and is actually end-to-end encrypted.
Comment · 12 years ago
There is a NeuroBayes plugin for TMVA. I've put it on Github with some additional patches: https://github.com/sroecker/tmva-neurobayes
Comment · 13 years ago
I did some research:
Around 0.6% of all Bitcoin are known to be lost, so with unknown losses it could be 1-2%(https://bitcointalk.org/index.php?topic=7253.120)
Excluding the Pirate scam, 2.9% have been stolen. These are still viable, some are tainted since the receiver address is known. (https://bitcointalk.org/index.php?topic=83794.0)
Comment · 13 years ago
It has been estimated on bitcointalk that around 1-2% have been lost. That's not really a large amount. You can still divide bitcoins into satoshis (1E-8) or even further with a protocol change in the future.