Marius
@rasmus1610.bsky.social
Applied AI, Neuroradiology, Web Development
Super interesting!
I'm currently evaluating the new gemini models for hand-written text extraction and somehow Gemini 2.0 Flash has problems with actual words. German or English, doesn't matter.
Haven't had the same problem with Flash Lite
I'm currently evaluating the new gemini models for hand-written text extraction and somehow Gemini 2.0 Flash has problems with actual words. German or English, doesn't matter.
Haven't had the same problem with Flash Lite
February 10, 2025 at 7:53 AM
Super interesting!
I'm currently evaluating the new gemini models for hand-written text extraction and somehow Gemini 2.0 Flash has problems with actual words. German or English, doesn't matter.
Haven't had the same problem with Flash Lite
I'm currently evaluating the new gemini models for hand-written text extraction and somehow Gemini 2.0 Flash has problems with actual words. German or English, doesn't matter.
Haven't had the same problem with Flash Lite
Reposted by Marius
Late last year I converted some of my projects to fastht.ml - and have been doing all new projects with it.
My productivity and enjoyment has increased significantly. An absolute joy to use. Thousand thanks to @howard.fm et al for the fantastic tooling.
My productivity and enjoyment has increased significantly. An absolute joy to use. Thousand thanks to @howard.fm et al for the fantastic tooling.
FastHTML
Modern web applications in pure Python
fastht.ml
February 7, 2025 at 6:43 AM
Late last year I converted some of my projects to fastht.ml - and have been doing all new projects with it.
My productivity and enjoyment has increased significantly. An absolute joy to use. Thousand thanks to @howard.fm et al for the fantastic tooling.
My productivity and enjoyment has increased significantly. An absolute joy to use. Thousand thanks to @howard.fm et al for the fantastic tooling.
Here is why I think reasoning models (like DeepSeek R1) are a huge step forward.
(and it's not necessarily their superior reasoning performance)
blog.mariusvach.com/posts/i-love...
(and it's not necessarily their superior reasoning performance)
blog.mariusvach.com/posts/i-love...
I love you, R1
Why I think reasoning models are a huge step forward...
blog.mariusvach.com
February 1, 2025 at 3:50 PM
Here is why I think reasoning models (like DeepSeek R1) are a huge step forward.
(and it's not necessarily their superior reasoning performance)
blog.mariusvach.com/posts/i-love...
(and it's not necessarily their superior reasoning performance)
blog.mariusvach.com/posts/i-love...
The effective use of LLMs IS a skill to be learned, just like using Google effectively is a skill too.
January 29, 2025 at 2:15 PM
The effective use of LLMs IS a skill to be learned, just like using Google effectively is a skill too.
Is there a vim mode for microsoft word?
vim motions really tend to infect everything you do on your computer.
vim motions really tend to infect everything you do on your computer.
January 27, 2025 at 10:22 AM
Is there a vim mode for microsoft word?
vim motions really tend to infect everything you do on your computer.
vim motions really tend to infect everything you do on your computer.
chat.deepseek.com seems to have some performance issues right now :D The hype got real.
DeepSeek
Chat with DeepSeek AI.
chat.deepseek.com
January 27, 2025 at 7:51 AM
chat.deepseek.com seems to have some performance issues right now :D The hype got real.
There is still room for an intuitive LLM app library like llama_index or langchain.
Man, these two libraries are a mess and so bloated. The source code is unreadable.
That's the problem when you try to do everything all at once.
Man, these two libraries are a mess and so bloated. The source code is unreadable.
That's the problem when you try to do everything all at once.
January 23, 2025 at 9:30 AM
There is still room for an intuitive LLM app library like llama_index or langchain.
Man, these two libraries are a mess and so bloated. The source code is unreadable.
That's the problem when you try to do everything all at once.
Man, these two libraries are a mess and so bloated. The source code is unreadable.
That's the problem when you try to do everything all at once.
Back from holidays to build cool shit and talk about it :)
January 16, 2025 at 2:40 PM
Back from holidays to build cool shit and talk about it :)
That’s one one my favorite posts by @morganhousel.bsky.social and there is some striking similarities to the work of Hartmut Rosa on ‚Resonance‘.
In the modern world we put too much emphasize on being efficient and correct.
Super interesting stuff.
collabfund.com/blog/intelli...
In the modern world we put too much emphasize on being efficient and correct.
Super interesting stuff.
collabfund.com/blog/intelli...
Intelligent vs. Smart
Here’s an important distinction to make in life.
collabfund.com
January 5, 2025 at 11:22 AM
That’s one one my favorite posts by @morganhousel.bsky.social and there is some striking similarities to the work of Hartmut Rosa on ‚Resonance‘.
In the modern world we put too much emphasize on being efficient and correct.
Super interesting stuff.
collabfund.com/blog/intelli...
In the modern world we put too much emphasize on being efficient and correct.
Super interesting stuff.
collabfund.com/blog/intelli...
It’s amazing how hard it is to beat BM25 for retrieval, especially in realms with specialized language like medicine.
December 17, 2024 at 10:06 AM
It’s amazing how hard it is to beat BM25 for retrieval, especially in realms with specialized language like medicine.
Super exiting stuff. I hope this will lead to smaller, more capable models!
Just 10 days after o1's public debut, we’re thrilled to unveil the open-source version of the technique behind its success: scaling test-time compute
By giving models more "time to think," Llama 1B outperforms Llama 8B in math—beating a model 8x its size. The full recipe is open-source!
By giving models more "time to think," Llama 1B outperforms Llama 8B in math—beating a model 8x its size. The full recipe is open-source!
December 16, 2024 at 10:29 PM
Super exiting stuff. I hope this will lead to smaller, more capable models!
editorialmanager.com is another business ready to be disrupted.
December 10, 2024 at 1:05 PM
editorialmanager.com is another business ready to be disrupted.
Reposted by Marius
I can now run a GPT-4 class model on my laptop
(The exact same laptop that could just about run a GPT-3 class model 20 months ago)
The new Llama 3.3 70B is a striking example of the huge efficiency gains we've seen in the last two years
simonwillison.net/2024/Dec/9/l...
(The exact same laptop that could just about run a GPT-3 class model 20 months ago)
The new Llama 3.3 70B is a striking example of the huge efficiency gains we've seen in the last two years
simonwillison.net/2024/Dec/9/l...
I can now run a GPT-4 class model on my laptop
Meta’s new Llama 3.3 70B is a genuinely GPT-4 class Large Language Model that runs on my laptop. Just 20 months ago I was amazed to see something that felt …
simonwillison.net
December 9, 2024 at 3:19 PM
I can now run a GPT-4 class model on my laptop
(The exact same laptop that could just about run a GPT-3 class model 20 months ago)
The new Llama 3.3 70B is a striking example of the huge efficiency gains we've seen in the last two years
simonwillison.net/2024/Dec/9/l...
(The exact same laptop that could just about run a GPT-3 class model 20 months ago)
The new Llama 3.3 70B is a striking example of the huge efficiency gains we've seen in the last two years
simonwillison.net/2024/Dec/9/l...
Nothing More - This is the Time (Ballast) - Live Drum Cam
YouTube video by Ben Anderson
www.youtube.com
December 8, 2024 at 11:54 AM
Reposted by Marius
New Blogpost!
How to use python decorators to define layouts in fastht.ml
blog.mariusvach.com/posts/decora...
How to use python decorators to define layouts in fastht.ml
blog.mariusvach.com/posts/decora...
FastHTML
Modern web applications in pure Python
fastht.ml
December 7, 2024 at 3:03 PM
New Blogpost!
How to use python decorators to define layouts in fastht.ml
blog.mariusvach.com/posts/decora...
How to use python decorators to define layouts in fastht.ml
blog.mariusvach.com/posts/decora...
After a very stressful AoC 2024 day 6, maybe today we'll do something easier: building a random forest library or some web dev.
That problem yesterday stressed me out :D
That problem yesterday stressed me out :D
December 7, 2024 at 10:19 AM
After a very stressful AoC 2024 day 6, maybe today we'll do something easier: building a random forest library or some web dev.
That problem yesterday stressed me out :D
That problem yesterday stressed me out :D
I love how fast you can spin up a jupyter lab instance using `uv`: `uv run --with jupyter jupyter lab`
This `uv run` is so helpful.
This `uv run` is so helpful.
December 5, 2024 at 6:14 PM
I love how fast you can spin up a jupyter lab instance using `uv`: `uv run --with jupyter jupyter lab`
This `uv run` is so helpful.
This `uv run` is so helpful.
I tried out the new SmolVLM model together with ColPali for a visual rag pipeline.
It's really nice to run everything on 15gb of VRAM.
Unfortunately, the QA abilities of SmolVLM are not as strong as I would have wished.
Here is a notebook with the code:
colab.research.google.com/drive/10ZnqA...
It's really nice to run everything on 15gb of VRAM.
Unfortunately, the QA abilities of SmolVLM are not as strong as I would have wished.
Here is a notebook with the code:
colab.research.google.com/drive/10ZnqA...
Google Colab
colab.research.google.com
November 28, 2024 at 7:26 PM
I tried out the new SmolVLM model together with ColPali for a visual rag pipeline.
It's really nice to run everything on 15gb of VRAM.
Unfortunately, the QA abilities of SmolVLM are not as strong as I would have wished.
Here is a notebook with the code:
colab.research.google.com/drive/10ZnqA...
It's really nice to run everything on 15gb of VRAM.
Unfortunately, the QA abilities of SmolVLM are not as strong as I would have wished.
Here is a notebook with the code:
colab.research.google.com/drive/10ZnqA...
That was fast:
The makers behind ColPali are already cooking up a version using the new SmolVLM model by @hf.co as the backbone.
Exciting stuff!
huggingface.co/vidore/colsm...
The makers behind ColPali are already cooking up a version using the new SmolVLM model by @hf.co as the backbone.
Exciting stuff!
huggingface.co/vidore/colsm...
vidore/colsmolvlm-alpha · Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
huggingface.co
November 28, 2024 at 6:34 PM
That was fast:
The makers behind ColPali are already cooking up a version using the new SmolVLM model by @hf.co as the backbone.
Exciting stuff!
huggingface.co/vidore/colsm...
The makers behind ColPali are already cooking up a version using the new SmolVLM model by @hf.co as the backbone.
Exciting stuff!
huggingface.co/vidore/colsm...
This little python class comes in very handy I you want to have javascript style function chaining like:
"Pipe(sample_text).pipe(split_into_words).pipe(convert_to_lowercase).pipe(remove_punctuation).pipe(count_words).value"
Python supports a much more functional programming style than I thought.
"Pipe(sample_text).pipe(split_into_words).pipe(convert_to_lowercase).pipe(remove_punctuation).pipe(count_words).value"
Python supports a much more functional programming style than I thought.
November 28, 2024 at 12:09 PM
This little python class comes in very handy I you want to have javascript style function chaining like:
"Pipe(sample_text).pipe(split_into_words).pipe(convert_to_lowercase).pipe(remove_punctuation).pipe(count_words).value"
Python supports a much more functional programming style than I thought.
"Pipe(sample_text).pipe(split_into_words).pipe(convert_to_lowercase).pipe(remove_punctuation).pipe(count_words).value"
Python supports a much more functional programming style than I thought.
One big advantage of a new social network is that you can curate your feed new.
I realized that I want to read more about AI/ML engineering/research and web development and less about indie hacking.
The first one is much more authentic…
I realized that I want to read more about AI/ML engineering/research and web development and less about indie hacking.
The first one is much more authentic…
November 28, 2024 at 5:57 AM
One big advantage of a new social network is that you can curate your feed new.
I realized that I want to read more about AI/ML engineering/research and web development and less about indie hacking.
The first one is much more authentic…
I realized that I want to read more about AI/ML engineering/research and web development and less about indie hacking.
The first one is much more authentic…