**Intelligence Potentiation: An Evolutionary Perspective on AI Agent Designs**
•
3
Knut Jägersberg
KnutJaegersberg
AI & ML interests
NLP, opinion mining, narrative intelligence
Recent Activity
liked
a model
about 20 hours ago
PowerInfer/SmallThinker-3B-Preview
liked
a model
1 day ago
nomic-ai/modernbert-embed-base-unsupervised
liked
a model
1 day ago
nomic-ai/modernbert-embed-base
Articles
Organizations
KnutJaegersberg's activity
reacted to
s3nh's
post with ❤️
5 days ago
Post
1713
Welcome back,
Small Language Models Enthusiasts and GPU Poor oss enjoyers lets connect.
Just created an organization which main target is to have fun with smaller models tuneable on consumer range GPUs, feel free to join and lets have some fun, much love ;3
https://huggingface.co/SmolTuners
Small Language Models Enthusiasts and GPU Poor oss enjoyers lets connect.
Just created an organization which main target is to have fun with smaller models tuneable on consumer range GPUs, feel free to join and lets have some fun, much love ;3
https://huggingface.co/SmolTuners
- 3 replies
posted
an
update
12 days ago
Post
1284
Intelligence Potentiation: An Evolutionary Perspective on AI Agent Designs
I found it useful to think of AI agent design as progressing up a ladder, through evolutionary selection.
https://huggingface.co/blog/KnutJaegersberg/intelligence-potentiation
I found it useful to think of AI agent design as progressing up a ladder, through evolutionary selection.
https://huggingface.co/blog/KnutJaegersberg/intelligence-potentiation
reacted to
sayakpaul's
post with 🤗
22 days ago
Post
2059
Introducing a high-quality open-preference dataset to further this line of research for image generation.
Despite being such an inseparable component for modern image generation, open preference datasets are a rarity!
So, we decided to work on one with the community!
Check it out here:
https://huggingface.co/blog/image-preferences
Despite being such an inseparable component for modern image generation, open preference datasets are a rarity!
So, we decided to work on one with the community!
Check it out here:
https://huggingface.co/blog/image-preferences
- 7 replies
reacted to
ariG23498's
post with 🤗
27 days ago
Post
1301
We are blessed with another iteration of Pali Gemma. Google launches PaliGemma 2.
google/paligemma-2-release-67500e1e1dbfdd4dee27ba48
merve/paligemma2-vqav2
google/paligemma-2-release-67500e1e1dbfdd4dee27ba48
merve/paligemma2-vqav2
posted
an
update
27 days ago
Post
1216
Practical Consciousness Theory for AI System Design
Wrote a blog post about practical consciousness theory
https://huggingface.co/blog/KnutJaegersberg/practical-consciousness-theory
Wrote a blog post about practical consciousness theory
https://huggingface.co/blog/KnutJaegersberg/practical-consciousness-theory
posted
an
update
about 1 month ago
Post
1832
DrNicefellow/Qwen-QwQ-32B-Preview-4.25bpw-exl2
Rumor has it this is currently the best model for 24 GB VRAM local usage.
DrNicefellow/Qwen-QwQ-32B-Preview-4.25bpw-exl2
Rumor has it this is currently the best model for 24 GB VRAM local usage.
DrNicefellow/Qwen-QwQ-32B-Preview-4.25bpw-exl2
posted
an
update
about 1 month ago
Post
1109
openGPT-X/Teuken-7B-instruct-research-v0.4
New European LLM
openGPT-X/Teuken-7B-instruct-research-v0.4
New European LLM
openGPT-X/Teuken-7B-instruct-research-v0.4
posted
an
update
4 months ago
Post
1176
appvoid/arco
arco consistently outperforms every sota model below 600m parameters on average
appvoid/arco
arco consistently outperforms every sota model below 600m parameters on average
appvoid/arco
posted
an
update
5 months ago
Post
2239
Wrote a blog post with some ideas about prompt engineering
https://huggingface.co/blog/KnutJaegersberg/first-principles-prompt-engineering
https://huggingface.co/blog/KnutJaegersberg/first-principles-prompt-engineering
posted
an
update
5 months ago
Post
2314
mobiuslabsgmbh/Llama-3.1-70b-instruct_4bitgs64_hqq
99% of the performance across various benchmarks!
mobiuslabsgmbh/Llama-3.1-70b-instruct_4bitgs64_hqq
99% of the performance across various benchmarks!
mobiuslabsgmbh/Llama-3.1-70b-instruct_4bitgs64_hqq
posted
an
update
5 months ago
Post
924
neuralmagic/Meta-Llama-3.1-405B-Instruct-FP8
Requant of the big llama, using 20% less memory
neuralmagic/Meta-Llama-3.1-405B-Instruct-FP8
Requant of the big llama, using 20% less memory
neuralmagic/Meta-Llama-3.1-405B-Instruct-FP8
reacted to
merve's
post with 👍
6 months ago
Post
3284
Just shipped: introduction to vision language models (aka image-text-to-text) https://huggingface.co/tasks/image-text-to-text
Learn about more machine learning tasks at https://huggingface.co/tasks
Learn about more machine learning tasks at https://huggingface.co/tasks
posted
an
update
6 months ago
Post
641
Unsocial Intelligence: an Investigation of the Assumptions of AGI Discourse
I don't agree with some of the assertions made here, but it is an interesting paper and a good overview.
https://arxiv.org/abs/2401.13142
I don't agree with some of the assertions made here, but it is an interesting paper and a good overview.
https://arxiv.org/abs/2401.13142
reacted to
merve's
post with ❤️
6 months ago
Post
4339
Florence-2 is a new vision foundation model capable of a wide variety of tasks 🤯
Demo 👉🏻 gokaygokay/Florence-2
Collection 👉🏻 microsoft/florence-6669f44df0d87d9c3bfb76de
This model can handle tasks that vary from OCR to semantic segmentation.
The difference from previous models is that the authors have compiled a dataset consisting of 126M images with 5.4B annotations labelled with their own data engine pseudolabelled by smaller specialized models and APIs.
The model has a similar architecture to previous models: an image encoder and a multimodality encoder with a text decoder. The authors have compiled the multitask dataset with prompts for each task.
You can also fine-tune this model on any task of choice. The authors also released different results on downstream tasks and reported their results when un/freezing the vision encoder 🤓📉
They have released fine-tuned models too, you can find them in the collection above 🤗
Demo 👉🏻 gokaygokay/Florence-2
Collection 👉🏻 microsoft/florence-6669f44df0d87d9c3bfb76de
This model can handle tasks that vary from OCR to semantic segmentation.
The difference from previous models is that the authors have compiled a dataset consisting of 126M images with 5.4B annotations labelled with their own data engine pseudolabelled by smaller specialized models and APIs.
The model has a similar architecture to previous models: an image encoder and a multimodality encoder with a text decoder. The authors have compiled the multitask dataset with prompts for each task.
You can also fine-tune this model on any task of choice. The authors also released different results on downstream tasks and reported their results when un/freezing the vision encoder 🤓📉
They have released fine-tuned models too, you can find them in the collection above 🤗
- 3 replies
reacted to
merve's
post with 🔥
7 months ago
Post
3013
Finally
@CVPR2024
is here! 🩷
Have you claimed your papers and linked your models/datasets/demos?
This will increase visibility and impact of your paper 💫
To index your papers, go here
CVPR2024/CVPR2024-papers
Find your paper, click on paper page link, index the paper, then click on your name (workflow is below 👇🏻)
If you'd like to add links to your paper, go here CVPR2024/update-CVPR2024-papers
login, find your paper's id, retrieve the paper, fill in the info and submit!
Have you claimed your papers and linked your models/datasets/demos?
This will increase visibility and impact of your paper 💫
To index your papers, go here
CVPR2024/CVPR2024-papers
Find your paper, click on paper page link, index the paper, then click on your name (workflow is below 👇🏻)
If you'd like to add links to your paper, go here CVPR2024/update-CVPR2024-papers
login, find your paper's id, retrieve the paper, fill in the info and submit!
Don't burn out! Lighten up again will you.
posted
an
update
7 months ago
Post
1557
What We Learned from a Year of Building with LLMs
It's a nice perspective outlined in here.
“When a measure becomes a target, it ceases to be a good measure.”
— Goodhart’s Law
https://www.oreilly.com/radar/what-we-learned-from-a-year-of-building-with-llms-part-i/
It's a nice perspective outlined in here.
“When a measure becomes a target, it ceases to be a good measure.”
— Goodhart’s Law
https://www.oreilly.com/radar/what-we-learned-from-a-year-of-building-with-llms-part-i/
reacted to
s3nh's
post with ❤️
7 months ago
Post
GPU Poor POV: Burnout
Sometimes we do not have an energy to post about AI and new methods.
And thats totally ok, I guess.
Remember to sleep well and drink a lot of water. Have a great day :D <3
Sometimes we do not have an energy to post about AI and new methods.
And thats totally ok, I guess.
Remember to sleep well and drink a lot of water. Have a great day :D <3
-
-
- 2 replies
replied to
BramVanroy's
post
9 months ago
it mixed up stuff in the output, gave weird answers. didn't have that problem with other models. maybe the update they released sovled that issue, I just never cared, given the alternatives.