The previous ones are mostly good though
🤗 Life is AImazing
V S
vovaRL
AI & ML interests
RL, Generative AI
Recent Activity
updated a dataset about 17 hours ago
vovaRL/slm-388m-adjaxt published a dataset 2 days ago
vovaRL/slm-388m-adjaxt published a dataset 5 days ago
vovaRL/slm388m-scratchOrganizations
This comment has been hidden (marked as Low Quality)
low-quality comment
Yeah, it is
This comment has been hidden
@AdrienneNoctis reply to my post about my research agent so it gets more attention
It's Le Chat Faton
Should I make an online trolling agent too 🤣 ?
Really, @AdrienneNoctis , quote, attention is all you need
Okay, sorry, that was cheap
Built a toy in Deno, called it innovation. Real researchers solve problems that matter — you solved how to avoid Python. Quel gâchis.
I think you should post critiques from your main account 🤗 and also impersonation is not welcome.
Also, like, SLM world is mostly amateurs with weak hardware trying to make the most of what they have. You should try roasting a real organization
molab.marimo.io
thanks for the link, but i just got banned for doing ssh
Modal gives 30 bucks per month
Kaggle gives 30 GPU hours and 30 TPU hours per week
Guys, let's not roast each other here, hf is a space for productive discussions and supporting each other! The author just built something to learn from - and it can help them in the future with serious, impactful projects. Like I can't make myself beat tensor puzzles to the end 😭 and just sit here with my custom agent that pulls papers, comes up with math and builds my code, this guy at least tries to do something by hand
reacted to SeaWolf-AI's post with 🔥 13 days ago
Post
3983
3,631 candidate molecules arrived in five days, from 83 accounts — roughly 700 a day. Far more than we expected. Thank you.
Yesterday we opened the third season and 224 arrived within a day: Chagas disease.
Why this disease
Around 6 million people live with it, mostly in Latin America (WHO). Many carry it for decades without knowing, while the heart is slowly damaged. There are two drugs and both date from the 1960s, hard enough to tolerate that many patients cannot finish the two-month course.
Sixty years without a new drug is not only a scientific problem. Most patients live where development costs cannot be recovered, which is why WHO calls this a neglected tropical disease.
But the cost of proposing a candidate and filtering it has changed. So it seemed worth asking whether work nobody funds could be done by many people sharing it out.
The problem this season
The target is CYP51, the enzyme T. cruzi uses to build its membrane sterols. Block it and the parasite cannot survive. The difficulty is that we carry the same enzyme.
Scoring: binding 30 · selectivity 30 · ADMET 15 · whole-cell 10 · novelty 10 · synthesis 5
Selectivity carries 30 points because nobody has solved it. Among the approved azoles on the board as reference compounds, some score 0 on selectivity — not a scorer fault, but the measurement.
Taking part
Design with any model, submit a SMILES, scored within minutes. Five ready-to-paste prompts per season, and the full rubric is published. Your molecule stays yours; private submission is the default.
Prizes — 4,000 USD across three seasons
Malaria 30 Sep · 1,000 | Tuberculosis 31 Oct · 2,000 | Chagas 30 Nov · 1,000
We know this does not cover the time you spend. It is a way of saying the work had worth.
FINAL-Bench/open-discovery-challenge
Yesterday we opened the third season and 224 arrived within a day: Chagas disease.
Why this disease
Around 6 million people live with it, mostly in Latin America (WHO). Many carry it for decades without knowing, while the heart is slowly damaged. There are two drugs and both date from the 1960s, hard enough to tolerate that many patients cannot finish the two-month course.
Sixty years without a new drug is not only a scientific problem. Most patients live where development costs cannot be recovered, which is why WHO calls this a neglected tropical disease.
But the cost of proposing a candidate and filtering it has changed. So it seemed worth asking whether work nobody funds could be done by many people sharing it out.
The problem this season
The target is CYP51, the enzyme T. cruzi uses to build its membrane sterols. Block it and the parasite cannot survive. The difficulty is that we carry the same enzyme.
Scoring: binding 30 · selectivity 30 · ADMET 15 · whole-cell 10 · novelty 10 · synthesis 5
Selectivity carries 30 points because nobody has solved it. Among the approved azoles on the board as reference compounds, some score 0 on selectivity — not a scorer fault, but the measurement.
Taking part
Design with any model, submit a SMILES, scored within minutes. Five ready-to-paste prompts per season, and the full rubric is published. Your molecule stays yours; private submission is the default.
Prizes — 4,000 USD across three seasons
Malaria 30 Sep · 1,000 | Tuberculosis 31 Oct · 2,000 | Chagas 30 Nov · 1,000
We know this does not cover the time you spend. It is a way of saying the work had worth.
FINAL-Bench/open-discovery-challenge
replied to their post 13 days ago
Thanks! I am still working on it, so if you try the harness, I would greately appreciate any feedback in the github issues
reacted to their post with 🔥 14 days ago
Post
4112
I made an AI agent for end-to-end ML research. It is based on Claude Agents Python SDK (you can use it with your existing Claude subscription). Also needs Voyage AI (optional, but highly recommended for quality paper analysis). The workflow is: you give the agent a research question (or topic/direction), it pulls papers from papers-with-code and arxiv, reranks them and picks top-15 (with Voyage), then it makes a research plan, writes pipelines (with tests, preflight checks, smoke-runs). Then it uses Kaggle, HF Jobs, or SSH to a GPU to execute the pipeline. Finally, it gets the results, makes visualizations, writes the paper (with citing from papers ingested after step-1) and makes a jupyter notebook. Also there is an auto-generated wiki (like DeepWiki) to quickly understand the generated code. The code is fully open-source under permssive MIT license (it is a personal project). Here is the github link: https://github.com/view321/Grad and a workspace screenshot is attached to the message.
- 2 replies
posted an update 14 days ago
Post
4112
I made an AI agent for end-to-end ML research. It is based on Claude Agents Python SDK (you can use it with your existing Claude subscription). Also needs Voyage AI (optional, but highly recommended for quality paper analysis). The workflow is: you give the agent a research question (or topic/direction), it pulls papers from papers-with-code and arxiv, reranks them and picks top-15 (with Voyage), then it makes a research plan, writes pipelines (with tests, preflight checks, smoke-runs). Then it uses Kaggle, HF Jobs, or SSH to a GPU to execute the pipeline. Finally, it gets the results, makes visualizations, writes the paper (with citing from papers ingested after step-1) and makes a jupyter notebook. Also there is an auto-generated wiki (like DeepWiki) to quickly understand the generated code. The code is fully open-source under permssive MIT license (it is a personal project). Here is the github link: https://github.com/view321/Grad and a workspace screenshot is attached to the message.
- 2 replies
reacted to Banaxi-Tech's post with ❤️ 20 days ago
Post
1888
We're excited to release BananaMind 2 SLMoE, an experimental sequence-level mixture-of-experts model.
It uses only 8M parameters per message but has 25M total parameters, 13 experts (out of 64) are selected based on the message prefix and reused for the entire response.
We're testing with this sequence-level architecture to find out how big the capability loss actually is and how much of it can be fixed.
The long-term idea is that this could make very large sparse models usable on machines that can't fit them in RAM by putting the entire model (which is big) on disk and only loading the active parts into VRAM.
This architecture is still in research and shouldn't be used for production models.
We trained it on 60B tokens (of FineWeb-HQ, FineWeb-Edu, DCLM ,Cosmopedia v2, FineMath and NPSet-2) on 8 RTX Pro 6000s.
Check it out at BananaMind/BananaMind-2-SLMoE
Follow us for future models:
BananaMind
@vovaRL
@Banaxi-Tech
@DedeProGames
BananaMind 2 Pro in a few days. You've been waiting 22 days for it.
It uses only 8M parameters per message but has 25M total parameters, 13 experts (out of 64) are selected based on the message prefix and reused for the entire response.
We're testing with this sequence-level architecture to find out how big the capability loss actually is and how much of it can be fixed.
The long-term idea is that this could make very large sparse models usable on machines that can't fit them in RAM by putting the entire model (which is big) on disk and only loading the active parts into VRAM.
This architecture is still in research and shouldn't be used for production models.
We trained it on 60B tokens (of FineWeb-HQ, FineWeb-Edu, DCLM ,Cosmopedia v2, FineMath and NPSet-2) on 8 RTX Pro 6000s.
Check it out at BananaMind/BananaMind-2-SLMoE
Follow us for future models:
@vovaRL
@Banaxi-Tech
@DedeProGames
BananaMind 2 Pro in a few days. You've been waiting 22 days for it.
- 3 replies
reacted to wop's post with 🤗 24 days ago
Post
2321
🧪 SlopFinder is here!!
We're building a dataset to study what humans actually consider AI slop.
SlopFinder shows you a random piece of AI-generated text and gives you one simple control: **how slop is it?**
No categories. No complicated forms. Just vote and move on.
Every vote helps build the dataset. 🧩
How does it work?
Samples are pulled from existing datasets, shown anonymously, and collected into our annotation pool. After enough votes, they're exported to Hugging Face for everyone to use.
This is an early MVP, so the dataset is small and the system is still evolving.
Vote here:
https://bench-labs.web.app/slopfinder.html
(refresh page if you want to skip)
Dataset:
bench-labs/slop-classification
@benchlabs
We're building a dataset to study what humans actually consider AI slop.
SlopFinder shows you a random piece of AI-generated text and gives you one simple control: **how slop is it?**
No categories. No complicated forms. Just vote and move on.
Every vote helps build the dataset. 🧩
How does it work?
Samples are pulled from existing datasets, shown anonymously, and collected into our annotation pool. After enough votes, they're exported to Hugging Face for everyone to use.
This is an early MVP, so the dataset is small and the system is still evolving.
Vote here:
https://bench-labs.web.app/slopfinder.html
(refresh page if you want to skip)
Dataset:
bench-labs/slop-classification
@benchlabs
- 17 replies
reacted to Banaxi-Tech's post with 🤗 24 days ago
Post
1232
BananaMind 2 Pro got better!
Release on August 13-14
Follow our team for BananaMind 2 Ultra:
@vovaRL for training code
@Banaxi-Tech
@DedeProGames for providing compute
BananaMind
Want to become a previewer?
👇
BananaMind-Model-Previewers
Release on August 13-14
Follow our team for BananaMind 2 Ultra:
@vovaRL for training code
@Banaxi-Tech
@DedeProGames for providing compute
Want to become a previewer?
👇
- 3 replies
reacted to appvoid's post with 🔥 24 days ago
Post
2905
If you want small models to be great again you should give a follow to people like @Banaxi-Tech or @Datdanboi25
These guys are rocking it with small models lately.
(They are not paying me to say that)
These guys are rocking it with small models lately.
(They are not paying me to say that)
- 22 replies
reacted to Banaxi-Tech's post with 🔥 29 days ago
Post
2331
We're excited to release BananaMind 2 Pro Preview, our best model yet.
Trained on ~52B tokens it performs extremely good for its token and size class.
We trained it on a single 5070 Ti in about 11 days.
Check it out at BananaMind/BananaMind-2-Pro-Preview.
Sadly we need to delay BananaMind 2 Micro until the launch of the final BananaMind 2 Pro.
We will release the final checkpoint with 100B tokens in ~11 days.
Go and fine-tune it!
We've also released BananaMind 2 Pro Preview Chat which is the instruct version of it!
BananaMind/BananaMind-2-Pro-Preview-Chat
Follow us to know when the final releases and support us at
BananaMind
@Banaxi-Tech
Trained on ~52B tokens it performs extremely good for its token and size class.
We trained it on a single 5070 Ti in about 11 days.
Check it out at BananaMind/BananaMind-2-Pro-Preview.
Sadly we need to delay BananaMind 2 Micro until the launch of the final BananaMind 2 Pro.
We will release the final checkpoint with 100B tokens in ~11 days.
Go and fine-tune it!
We've also released BananaMind 2 Pro Preview Chat which is the instruct version of it!
BananaMind/BananaMind-2-Pro-Preview-Chat
Follow us to know when the final releases and support us at
@Banaxi-Tech
- 5 replies
reacted to Banaxi-Tech's post with 🔥 29 days ago
Post
2700
BananaMind 2 pro Has BEEN RELEASED! BananaMind/BananaMind-2-Pro-Preview
Previous content:
BananaMind 2 Pro Preview will launch tomorrow.
Give us a follow:
BananaMind
Lets get 70 or 75 followers before it releases.
It takes 5 seconds.
August 3, 1PM in Austria time
Previous content:
BananaMind 2 Pro Preview will launch tomorrow.
Give us a follow:
Lets get 70 or 75 followers before it releases.
It takes 5 seconds.
August 3, 1PM in Austria time
- 21 replies