Armin Buescher

Security Researcher. Disclaimer: my tweets don't reflect the views of my current or past employers!

[Armin Buescher @armbues]

@lucataco93 Nice!
FYI peak memory during training depends on batch size and # tokens in the dataset.
You should give SiLLM a try for training with LoRA/DPO: https://t.co/hf4uTSX6xV

[Armin Buescher @armbues]

@DaveDC22 There was a bug that was fixed in the app. Pull the latest source from the repo and it should work 👍

[Armin Buescher @armbues]

Running Llama-3-8B-Instruct on Mac with the SiLLM framework powered by MLX... just took some fiddling with the tokenizer & template to get it to run 😁

[Armin Buescher @armbues]

@DaveDC22 You need to point it at a directory with model files that you want to run. What type of model are you trying to load?

[Armin Buescher @armbues]

@awnihannun I could not agree more! 💯
Fantastic job by the team working on this! 👏

[Armin Buescher @armbues]

@alew3 @awnihannun An out-of-the-box solution to run/train LLMs on Apple Silicon built on top of MLX:
https://t.co/hf4uTSX6xV

[Armin Buescher @armbues]

Early version bump for SiLLM to 0.1.1 with some bugfixes and support for Llama-3 models.
https://t.co/LQpOjOTlbA
https://t.co/hf4uTSX6xV

[Armin Buescher @armbues]

@adithyan_ai Just loading the model needs about 87 GB and then you’d need a bit more for inference.

[Armin Buescher @armbues]

Running WizardLM-2-8x22B 4-bit quantized on a Mac Studio with SiLLM powered by Apple MLX

[Armin Buescher @armbues]

@ivanfioravanti @awnihannun Just the product of lots of tinkering and trying to port DPO & losses over to MLX 😁
Might have some bugs that I'm not seeing 🙈
Example code with the DPO-mix dataset here: https://t.co/h7GvQ6rat2

[Armin Buescher @armbues]

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 👏

[Armin Buescher @armbues]

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:
https://t.co/hf4uTSX6xV

[Armin Buescher @armbues]

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

[CARO Workshop 2027 @caroworkshop]

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.

https://t.co/PDawMvhhv8

[Socially Distant Jerry @Maliciouslink]

Y’all have a home on https://t.co/F199jufn1i if you need it ❤️

[StupidBird @Legen78695928]

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！

[Joe Desimone @dez_]

We just released 1000+ yara rules and 200+ endpoint behavior rules https://t.co/33PMWZIlky

[Armin Buescher @armbues]

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 🥳