**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
2 days ago
NX-AI/xLSTM-7b
liked
a model
2 days ago
ibm-fms/Bamba-9B
liked
a model
2 days ago
OpenGVLab/InternVL2_5-38B-MPO
Articles
Organizations
KnutJaegersberg's activity
posted
an
update
6 days ago
Post
1228
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 🤗
15 days ago
Post
2040
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 🤗
20 days ago
Post
1283
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
20 days ago
Post
1203
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
25 days ago
Post
1830
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
29 days ago
Post
1107
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
1175
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
4 months ago
Post
2237
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
4 months ago
Post
2313
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
640
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 🔥
6 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
1556
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.
reacted to
BramVanroy's
post with 👍
9 months ago
Post
2392
Does anyone have experience with finetuning Gemma? Even the 2B variant feels more memory heavy than mistral 7B. I know that its vocabulary is much larger (250k) but I'm a bit surprised that the max batch size that I can get in an A100 80GB is only 2 whereas I could fit 4 with mistral 7B - even though Gemma is much smaller except for the embedding layer. Both runs were using FA, same sequence length, same deepspeed zero 3 settings. Oh and yes I'm using the most recent hot fix of transformers that solves a memory issue with Gemma and others.
Any prior experience that you can share or suggestions to improve throughout?
Any prior experience that you can share or suggestions to improve throughout?
-
- 4 replies