Viewing profile — strickvl

Hi HN, I am one of the people behind Kitaru. Over the last year, we kept seeing teams in our ZenML community stretch pipeline DAGs to run agents; they executed things like dynamic …

Author here. I work at ZenML, where we maintain the LLMOps Database ( https://www.zenml.io/llmops-database ) — a collection of production LLM case studies we've been cataloguing fo…

I've spent weeks curating technical implementation details of how companies are actually deploying LLMs and Generative AI in production. The database now contains over 300 case stu…

But still only single GPU for now. I also heard great things about it, but wanted to make the maximum use of my multi-GPU local setup.

Thanks! Yes one 'next step' that I'd like to do (probably around the work on deployment / inference that I'm turning to now) will be to see just how small I can get the model. Spac…

Interesting. I can maybe try finetuning one or two of the so-called 'uncensored' open models and see if that makes a difference. A bit harder to switch out the dataset completely, …

OpenpPipe - https://openpipe.ai/ - is probably the service that most closely resembles what you’re asking for, but I found the evals weren’t really what I wanted — i.e. following m…

I followed whatever the guidance was for a specific model. Some of the LLM finetuning providers did indeed set the temperature to 0 and I followed that, but others suggested 1. I c…

Depends a bit where you’re running etc. This works for Modal, e.g., but they’re just using axolotl under the hood so you can just connect to whatever cloud provider of choice you’r…

I think not. Normally if you get those kinds of errors you wouldn’t get any output at all. In the blog I show that all 724 of the test cases got proper JSON output etc for the quer…

There's a ton of abstraction in axolotl, for sure, but so far I haven't found that it gets in the way. The main competitor in that space seems to be Unsloth, but that only works wi…

ZenML | Developer Advocate | Full-time | Remote (Europe / UK) | https://zenml.io Hey! We are an open-source company ( https://github.com/zenml-io/zenml ) and the pulse of ZenML's c…

If you're in the UK, Pimoroni ( https://shop.pimoroni.com/?q=solar ) has some good options as well.

Location: London (United Kingdom / UK) Remote: Willing to be fully remote / hybrid. Willing to relocate: Yes (Germany or the Netherlands would work well) Technologies: Ruby, JavaSc…

Location: London (United Kingdom / UK) Remote: Willing to be fully remote / hybrid. Willing to relocate: Yes. Technologies: Ruby, JavaScript (ES6, Node.js), Python, Go, React, Redu…