I'm excited to share a new open-source project: the Silicon LLM Training & Inference Toolkit, short SiLLM.
Check out the project on Github here:
github.com/armbues/SiLLM
The repository includes several code examples:
- LoRA training with the Nvidia HelpSteer dataset
- DPO Fine-tuning with the DPO Mix 7K dataset
- Implementation of the MMLU Benchmark
- Calculating perplexity scores of a model for a sample dataset
A huge thank you to @awnihannun@angeloskath and the rest of the team for developing the MLX framework that SiLLM relies on! Also big kudos to all the contributors of the MLX Examples project 👏
One of the reasons to attend the #CARO2023 is the food for thought that is delivered in talks, conversations, and of course keynotes. Armin Büscher @armbues will share his technical perspective about innovation and disruption in cybersecurity.
caro2023.org/#c228106
This file leaked an Security Enterprise Virustotal API Key before!But now it's expired because someone leaked the key😅
ITW:07c4a75b1422a22ec29c5102e0b67055
API Key:d10468bead05da1685629a0abcfed5f963d6adbc7e6bb2b2fc343dbb36be0349
unbelievable!
I'll be traveling to Vegas for #blackhat2022 and #DEFCON next week. Looking forward to hang out with many infosec folks I haven't seen in a long time 🥳
The last seven years of my life have been wild, full of weirdos, spies, outlandish discoveries, sleuthing, hangovers, bungling criminals, madcap schemes, Libyan militias and Russian nerve gas. And it’s all in this book, out June 2022. Order your copy here: penguin.co.uk/books/1444756/…
Just bought a ticket for @ruhrsec day next month. First conference for me in a long time - I'm really looking forward to attending some interesting talks and hanging out after. #ruhrsec