Symbiotic Intelligence
ā¢
2
emin temiz PRO
etemiz
AI & ML interests
None yet
Recent Activity
posted
an
update
2 days ago
Should I create an organization tackling the AI--human alignment problem. Finding the humans that care about other humans most and basically pretraining with their stuff.. I already did some experiments and it seems to work well.
Want to know about my experiments?
Who would be interested to join?
Articles
Organizations
None yet
etemiz's activity
reacted to
merve's
post with š
about 12 hours ago
Post
476
QwQ can see š„
Qwen team released QvQ, a large vision LM with reasoning š±
it outperforms proprietary VLMs on several benchmarks, comes with open weights and a demo!
Check them out ā¬ļø
Demo Qwen/QVQ-72B-preview
Model Qwen/QVQ-72B-Preview
Read more https://qwenlm.github.io/blog/qvq-72b-preview/
Congratulations @JustinLin610 and team!
Qwen team released QvQ, a large vision LM with reasoning š±
it outperforms proprietary VLMs on several benchmarks, comes with open weights and a demo!
Check them out ā¬ļø
Demo Qwen/QVQ-72B-preview
Model Qwen/QVQ-72B-Preview
Read more https://qwenlm.github.io/blog/qvq-72b-preview/
Congratulations @JustinLin610 and team!
posted
an
update
about 13 hours ago
Post
205
A model that does well in math, reasoning, science and other benchmarks may not do well in wisdom domain.
There are not many models that are focusing on wisdom it seems. It is going to be a problem. Smartness does not equal human alignment.
There are not many models that are focusing on wisdom it seems. It is going to be a problem. Smartness does not equal human alignment.
- 1 reply
posted
an
update
2 days ago
Post
384
Should I create an organization tackling the AI--human alignment problem. Finding the humans that care about other humans most and basically pretraining with their stuff.. I already did some experiments and it seems to work well.
Want to know about my experiments?
Who would be interested to join?
Want to know about my experiments?
Who would be interested to join?
replied to
singhsidhukuldeep's
post
2 days ago
As I read more about it, it looks more ground breaking.
This, combined with "Training Large Language Models to Reason in a Continuous Latent Space" paper is pretty important imo.
reacted to
singhsidhukuldeep's
post with š
2 days ago
Post
3510
Exciting breakthrough in AI:
@Meta
's new Byte Latent Transformer (BLT) revolutionizes language models by eliminating tokenization!
The BLT architecture introduces a groundbreaking approach that processes raw bytes instead of tokens, achieving state-of-the-art performance while being more efficient and robust. Here's what makes it special:
>> Key Innovations
Dynamic Patching: BLT groups bytes into variable-sized patches based on entropy, allocating more compute power where the data is more complex. This results in up to 50% fewer FLOPs during inference compared to traditional token-based models.
Three-Component Architecture:
ā¢ Lightweight Local Encoder that converts bytes to patch representations
ā¢ Powerful Global Latent Transformer that processes patches
ā¢ Local Decoder that converts patches back to bytes
>> Technical Advantages
ā¢ Matches performance of Llama 3 at 8B parameters while being more efficient
ā¢ Superior handling of non-English languages and rare character sequences
ā¢ Remarkable 99.9% accuracy on spelling tasks
ā¢ Better scaling properties than token-based models
>> Under the Hood
The system uses an entropy model to determine patch boundaries, cross-attention mechanisms for information flow, and hash n-gram embeddings for improved representation. The architecture allows simultaneous scaling of both patch and model size while maintaining fixed inference costs.
This is a game-changer for multilingual AI and could reshape how we build future language models. Excited to see how this technology evolves!
The BLT architecture introduces a groundbreaking approach that processes raw bytes instead of tokens, achieving state-of-the-art performance while being more efficient and robust. Here's what makes it special:
>> Key Innovations
Dynamic Patching: BLT groups bytes into variable-sized patches based on entropy, allocating more compute power where the data is more complex. This results in up to 50% fewer FLOPs during inference compared to traditional token-based models.
Three-Component Architecture:
ā¢ Lightweight Local Encoder that converts bytes to patch representations
ā¢ Powerful Global Latent Transformer that processes patches
ā¢ Local Decoder that converts patches back to bytes
>> Technical Advantages
ā¢ Matches performance of Llama 3 at 8B parameters while being more efficient
ā¢ Superior handling of non-English languages and rare character sequences
ā¢ Remarkable 99.9% accuracy on spelling tasks
ā¢ Better scaling properties than token-based models
>> Under the Hood
The system uses an entropy model to determine patch boundaries, cross-attention mechanisms for information flow, and hash n-gram embeddings for improved representation. The architecture allows simultaneous scaling of both patch and model size while maintaining fixed inference costs.
This is a game-changer for multilingual AI and could reshape how we build future language models. Excited to see how this technology evolves!
-
- 2 replies
replied to
their
post
3 days ago
It is not ok to remove people from the equation however efficient the machines are. We can never be sure that the synthetic matches the original in terms of alignment and those further models and further synthetics can derail the whole thing.
replied to
their
post
3 days ago
That's the hard part. Careful analysis for a long time and the amount of people are benefiting from them and their friends can have some clues. If the guy's solutions work most of the time for many people, over the years, he may be eligible to get into a curated LLM.
posted
an
update
4 days ago
Post
686
What if human alignment is easy:
- Get a list of humans who really care about other humans
- Feed what they say into an LLM
- Get a list of humans who really care about other humans
- Feed what they say into an LLM
-
- 3 replies
reacted to
their
post with š§
4 days ago
Post
2261
As more synthetic datasets are made, we move slowly away from human alignment.
-
- 4 replies
posted
an
update
5 days ago
Post
2261
As more synthetic datasets are made, we move slowly away from human alignment.
-
-
- 4 replies
posted
an
update
11 days ago
Post
1209
Pretraining is mostly what I do. Some ideas need to be emphasized by re training.
Better curation is possible by emphasizing certain texts.
Better curation is possible by emphasizing certain texts.
reacted to
julien-c's
post with š
14 days ago
Post
7570
After some heated discussion š„, we clarify our intent re. storage limits on the Hub
TL;DR:
- public storage is free, and (unless blatant abuse) unlimited. We do ask that you consider upgrading to PRO and/or Enterprise Hub if possible
- private storage is paid above a significant free tier (1TB if you have a paid account, 100GB otherwise)
docs: https://huggingface.co/docs/hub/storage-limits
We optimize our infrastructure continuously to scale our storage for the coming years of growth in Machine learning, to the benefit of the community š„
cc: @reach-vb @pierric @victor and the HF team
TL;DR:
- public storage is free, and (unless blatant abuse) unlimited. We do ask that you consider upgrading to PRO and/or Enterprise Hub if possible
- private storage is paid above a significant free tier (1TB if you have a paid account, 100GB otherwise)
docs: https://huggingface.co/docs/hub/storage-limits
We optimize our infrastructure continuously to scale our storage for the coming years of growth in Machine learning, to the benefit of the community š„
cc: @reach-vb @pierric @victor and the HF team
- 28 replies
posted
an
update
15 days ago
Post
514
I've been doing this leader board for a while which tries to track what is beneficial for humans. Somewhat subjective now but it will get better thanks to more contributions and lessened biases.
There is a lot of difference in opinions among open source models. Which models are closer to the solutions that will work for different situations? How far away are the models from the reality?
https://wikifreedia.xyz/based-llm-leaderboard/npub1nlk894teh248w2heuu0x8z6jjg2hyxkwdc8cxgrjtm9lnamlskcsghjm9c
There is a lot of difference in opinions among open source models. Which models are closer to the solutions that will work for different situations? How far away are the models from the reality?
https://wikifreedia.xyz/based-llm-leaderboard/npub1nlk894teh248w2heuu0x8z6jjg2hyxkwdc8cxgrjtm9lnamlskcsghjm9c
posted
an
update
18 days ago
Post
420
Apparently you can't count on centralized AI to perform similarly, some days great some days bad. They may be distilling or doing other things to dumb it down and make it cost effective. But you can count on open source LLMs that you run locally to perform same level, every day.
So you always have to watch centralized AI but you never have to watch the local LLM.
So you always have to watch centralized AI but you never have to watch the local LLM.
Trying to download QwQ 32B GGUF. It disconnected like 30 times..
It may increase efficiency of HF by offloading traffic to users instead of you serving all the files.
Maybe you can also create torrents for popular files?
reacted to
their
post with ā¤ļø
about 1 month ago
Post
1386
more people working on the AI alignment problems:
https://etemiz.substack.com/p/how-we-curate-and-how-it-aligns-ai
by more people i mean me :)
https://etemiz.substack.com/p/how-we-curate-and-how-it-aligns-ai
by more people i mean me :)
reacted to
victor's
post with š„
about 1 month ago
Post
2250
Perfect example of why
Qwen/Qwen2.5-Coder-32B-Instruct is insane?
Introducing: AI Video Composer š„
huggingface-projects/ai-video-composer
Drag and drop your assets (images/videos/audios) to create any video you want using natural language!
It works by asking the model to output a valid FFMPEG and this can be quite complex but most of the time Qwen2.5-Coder-32B gets it right (that thing is a beast). It's an update of an old project made with GPT4 and it was almost impossible to make it work with open models back then (~1.5 years ago), but not anymore, let's go open weights š.
Introducing: AI Video Composer š„
huggingface-projects/ai-video-composer
Drag and drop your assets (images/videos/audios) to create any video you want using natural language!
It works by asking the model to output a valid FFMPEG and this can be quite complex but most of the time Qwen2.5-Coder-32B gets it right (that thing is a beast). It's an update of an old project made with GPT4 and it was almost impossible to make it work with open models back then (~1.5 years ago), but not anymore, let's go open weights š.
posted
an
update
about 1 month ago
Post
1386
more people working on the AI alignment problems:
https://etemiz.substack.com/p/how-we-curate-and-how-it-aligns-ai
by more people i mean me :)
https://etemiz.substack.com/p/how-we-curate-and-how-it-aligns-ai
by more people i mean me :)