Lucas Beyer (bl16)
@giffmana.ai
Researcher (OpenAI. Ex: DeepMind, Brain, RWTH Aachen), Gamer, Hacker, Belgian.
Anon feedback: https://admonymous.co/giffmana
📍 Zürich, Suisse 🔗 http://lucasb.eyer.be
Anon feedback: https://admonymous.co/giffmana
📍 Zürich, Suisse 🔗 http://lucasb.eyer.be
I noticed that I'm not using bsky much anymore. Not sure why, vibes.
Anyways, someone noticing that DeepSeek refuses to answer *anything* about Xi Jinping, even the question whether he exists at all, triggered me writing a short snippet on safety fine-tuning: lb.eyer.be/s/safety-sft...
Anyways, someone noticing that DeepSeek refuses to answer *anything* about Xi Jinping, even the question whether he exists at all, triggered me writing a short snippet on safety fine-tuning: lb.eyer.be/s/safety-sft...
January 26, 2025 at 9:21 PM
I noticed that I'm not using bsky much anymore. Not sure why, vibes.
Anyways, someone noticing that DeepSeek refuses to answer *anything* about Xi Jinping, even the question whether he exists at all, triggered me writing a short snippet on safety fine-tuning: lb.eyer.be/s/safety-sft...
Anyways, someone noticing that DeepSeek refuses to answer *anything* about Xi Jinping, even the question whether he exists at all, triggered me writing a short snippet on safety fine-tuning: lb.eyer.be/s/safety-sft...
First candidate for banger of the year appeared, only 2 days in:
January 2, 2025 at 10:26 PM
First candidate for banger of the year appeared, only 2 days in:
Not quite because this one is not stacked, so I give it better chance to scale:
December 19, 2024 at 8:24 AM
Not quite because this one is not stacked, so I give it better chance to scale:
A post by @cloneofsimo on Twitter made me write up some lore about residuals, ResNets, and Transformers. And I couldn't resist sliding in the usual cautionary tale about small/mid-scale != large-scale.
Blogpost: lb.eyer.be/s/residuals....
Blogpost: lb.eyer.be/s/residuals....
December 18, 2024 at 11:14 PM
A post by @cloneofsimo on Twitter made me write up some lore about residuals, ResNets, and Transformers. And I couldn't resist sliding in the usual cautionary tale about small/mid-scale != large-scale.
Blogpost: lb.eyer.be/s/residuals....
Blogpost: lb.eyer.be/s/residuals....
Good morning Vancouver!
Things are different here: this guy is alone, chonky, and not scared at all, I was more scared of him towards the end lol.
Also look at that … industrialization
Things are different here: this guy is alone, chonky, and not scared at all, I was more scared of him towards the end lol.
Also look at that … industrialization
December 10, 2024 at 6:09 PM
Good morning Vancouver!
Things are different here: this guy is alone, chonky, and not scared at all, I was more scared of him towards the end lol.
Also look at that … industrialization
Things are different here: this guy is alone, chonky, and not scared at all, I was more scared of him towards the end lol.
Also look at that … industrialization
Good morning! On my way to NeurIPS, slightly sad to leave this beautiful place and my family for the week, but also excited to meet many new and old friends at NeurIPS!
December 9, 2024 at 8:40 AM
Good morning! On my way to NeurIPS, slightly sad to leave this beautiful place and my family for the week, but also excited to meet many new and old friends at NeurIPS!
Yes. ViT is not inspired by nonlocal paper at all, and I may even have been the only person (or close to that) in the project who knew nonlocal paper.
I’m not saying this as a hater, I liked nonlocal:
I’m not saying this as a hater, I liked nonlocal:
December 6, 2024 at 11:27 PM
Yes. ViT is not inspired by nonlocal paper at all, and I may even have been the only person (or close to that) in the project who knew nonlocal paper.
I’m not saying this as a hater, I liked nonlocal:
I’m not saying this as a hater, I liked nonlocal:
It's relatively long, so just a few highlights:
1. It works really well on GPUs out of the box.
2. I made ready-to-go docker templates for runpod.
3. Fine-tuning is cheap!! A sweep of 72 runs cost me less than $1
4. PaliGemma and SigLIP nail the "line intersections" task with 128 examples:
1. It works really well on GPUs out of the box.
2. I made ready-to-go docker templates for runpod.
3. Fine-tuning is cheap!! A sweep of 72 runs cost me less than $1
4. PaliGemma and SigLIP nail the "line intersections" task with 128 examples:
December 3, 2024 at 12:18 AM
It's relatively long, so just a few highlights:
1. It works really well on GPUs out of the box.
2. I made ready-to-go docker templates for runpod.
3. Fine-tuning is cheap!! A sweep of 72 runs cost me less than $1
4. PaliGemma and SigLIP nail the "line intersections" task with 128 examples:
1. It works really well on GPUs out of the box.
2. I made ready-to-go docker templates for runpod.
3. Fine-tuning is cheap!! A sweep of 72 runs cost me less than $1
4. PaliGemma and SigLIP nail the "line intersections" task with 128 examples:
Our big_vision codebase is really good! And it's *the* reference for ViT, SigLIP, PaliGemma, JetFormer, ... including fine-tuning them.
However, it's criminally undocumented. I tried using it outside Google to fine-tune PaliGemma and SigLIP on GPUs, and wrote a tutorial: lb.eyer.be/a/bv_tuto.html
However, it's criminally undocumented. I tried using it outside Google to fine-tune PaliGemma and SigLIP on GPUs, and wrote a tutorial: lb.eyer.be/a/bv_tuto.html
December 3, 2024 at 12:18 AM
Our big_vision codebase is really good! And it's *the* reference for ViT, SigLIP, PaliGemma, JetFormer, ... including fine-tuning them.
However, it's criminally undocumented. I tried using it outside Google to fine-tune PaliGemma and SigLIP on GPUs, and wrote a tutorial: lb.eyer.be/a/bv_tuto.html
However, it's criminally undocumented. I tried using it outside Google to fine-tune PaliGemma and SigLIP on GPUs, and wrote a tutorial: lb.eyer.be/a/bv_tuto.html
Haven't actually read it yet, but man, this image is beautiful and perfect, well done:
December 2, 2024 at 8:24 PM
Haven't actually read it yet, but man, this image is beautiful and perfect, well done:
Yeah but don’t think this was somehow a US exposure thing.
Funnily relevant to this discussion, „Bundeswehr university“ literally means defense/military university.
Funnily relevant to this discussion, „Bundeswehr university“ literally means defense/military university.
November 30, 2024 at 9:05 PM
Yeah but don’t think this was somehow a US exposure thing.
Funnily relevant to this discussion, „Bundeswehr university“ literally means defense/military university.
Funnily relevant to this discussion, „Bundeswehr university“ literally means defense/military university.
Some recent discussions made me write up a short read on how I think about doing computer vision research when there's clear potential for abuse.
Alternative title: why I decided to stop working on tracking.
Curious about other's thoughts on this.
lb.eyer.be/s/cv-ethics....
Alternative title: why I decided to stop working on tracking.
Curious about other's thoughts on this.
lb.eyer.be/s/cv-ethics....
November 29, 2024 at 2:51 PM
Some recent discussions made me write up a short read on how I think about doing computer vision research when there's clear potential for abuse.
Alternative title: why I decided to stop working on tracking.
Curious about other's thoughts on this.
lb.eyer.be/s/cv-ethics....
Alternative title: why I decided to stop working on tracking.
Curious about other's thoughts on this.
lb.eyer.be/s/cv-ethics....
Aaaaand it's starting:
November 29, 2024 at 11:46 AM
Aaaaand it's starting:
I must be on some kind of list or something lol
November 28, 2024 at 7:44 PM
I must be on some kind of list or something lol
segment cow
not on the beach, but as you may know I like cows in "out of distribution" places and poses.
huggingface.co/spaces/big-v...
not on the beach, but as you may know I like cows in "out of distribution" places and poses.
huggingface.co/spaces/big-v...
November 28, 2024 at 11:37 AM
segment cow
not on the beach, but as you may know I like cows in "out of distribution" places and poses.
huggingface.co/spaces/big-v...
not on the beach, but as you may know I like cows in "out of distribution" places and poses.
huggingface.co/spaces/big-v...
Sorry, but I was strangely attracted... @5trange4ttractor.bsky.social =D
November 27, 2024 at 9:01 PM
Sorry, but I was strangely attracted... @5trange4ttractor.bsky.social =D
Here's Gemini latest, which is wrong in both variants, and also yaps way too much :(
November 27, 2024 at 8:38 PM
Here's Gemini latest, which is wrong in both variants, and also yaps way too much :(
Here's a fun real-life prompt where 30min of Googling didn't really help me.
The small/fast/mini chatbots all failed miserably
The large ones work great (except Gemini).
Also:
1. I really like C3.6 giving only answer and asking if explain
2. Wild that Chat understood the calls and added comments!
The small/fast/mini chatbots all failed miserably
The large ones work great (except Gemini).
Also:
1. I really like C3.6 giving only answer and asking if explain
2. Wild that Chat understood the calls and added comments!
November 27, 2024 at 8:38 PM
Here's a fun real-life prompt where 30min of Googling didn't really help me.
The small/fast/mini chatbots all failed miserably
The large ones work great (except Gemini).
Also:
1. I really like C3.6 giving only answer and asking if explain
2. Wild that Chat understood the calls and added comments!
The small/fast/mini chatbots all failed miserably
The large ones work great (except Gemini).
Also:
1. I really like C3.6 giving only answer and asking if explain
2. Wild that Chat understood the calls and added comments!
Reminder that robots.txt is a gentleman’s agreement, not a legal document.
The good actors all respect it, but there’s many bad actors out there on the internet.
The good actors all respect it, but there’s many bad actors out there on the internet.
November 27, 2024 at 8:45 AM
Reminder that robots.txt is a gentleman’s agreement, not a legal document.
The good actors all respect it, but there’s many bad actors out there on the internet.
The good actors all respect it, but there’s many bad actors out there on the internet.
A sunny winter morning near the lake in Zürich is probably one of the best mood enhancers available world-wide.
I don't think I'll ever get tired of this.
I don't think I'll ever get tired of this.
November 26, 2024 at 2:41 PM
A sunny winter morning near the lake in Zürich is probably one of the best mood enhancers available world-wide.
I don't think I'll ever get tired of this.
I don't think I'll ever get tired of this.
Also switched my main server from nginx to Caddy.
I'm quite liking it so far: https works out of the box and for free, and the whole configuration got shorter and more readable.
I'm quite liking it so far: https works out of the box and for free, and the whole configuration got shorter and more readable.
November 25, 2024 at 8:22 PM
Also switched my main server from nginx to Caddy.
I'm quite liking it so far: https works out of the box and for free, and the whole configuration got shorter and more readable.
I'm quite liking it so far: https works out of the box and for free, and the whole configuration got shorter and more readable.
