Hugging Face's logo

The Waifu Research Department
community
Activity Feed Request to join this org

AI & ML interests

Waifu and Husbando Research

Recent Activity

yuna0x0  authored a paper 28 days ago
See, Point, Fly: A Learning-Free VLM Framework for Universal Unmanned Aerial Navigation
Skylion007  authored a paper 4 months ago
The Diffusion Duality
Skylion007  authored a paper 8 months ago
Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models
View all activity

s3nh 
posted an update 10 days ago
view post
Post
436
Eduhelp with more empathy, based on model finetuned on
psychotheraputic preferences just landed on


Beck-8B as a base model, 13000 steps on educational dataset.
Time to go further and build more 🥰
s3nh/EduHelp_Beck_8B
Thanks to @basilic_ai for computations <3
s3nh 
posted an update 12 days ago
view post
Post
4010
Just tried to create an educational assistant for younger people who can struggle with visualsation of 'what is this sorcery all about'.
Its first step of my spare time projects, sft on Qwen3-8B,

EduHelper is a child-friendly tutoring assistant fine-tuned from the Qwen3-8B base model using parameter-efficient fine-tuning (PEFT) with LoRA on the ajibawa-2023/Education-Young-Children dataset.

s3nh/EduHelp-8B

Glad to share my work, have a wonderful day!
  • 2 replies
·
narugo1992 
authored a paper 17 days ago
yuna0x0 
authored a paper 28 days ago
innovation64 
authored a paper about 1 month ago
Tonic 
posted an update about 1 month ago
Tonic 
posted an update about 1 month ago
view post
Post
667
COMPUTER CONTROL IS ON-DEVICE !

🏡🤖 78 % of EU smart-home owners DON’T trust cloud voice assistants.

So we killed the cloud.

Meet Exté: a palm-sized Android device that sees, hears & speaks your language - 100 % offline, 0 % data sent anywhere.

🔓 We submitted our technologies for consideration to the Liquid AI hackathon.

📊 Dataset: 79 k UI-action pairs on Hugging Face (largest Android-control corpus ever) Tonic/android-operator-episodes

⚡ Model: 98 % task accuracy, 678MB compressed , fits on existing android devices ! Tonic/l-android-control

🛤️ Experiment Tracker : check out the training on our TrackioApp Tonic/l-android-control

🎮 Live Model Demo: Upload an Android Screenshot and instructions to see the model in action ! Tonic/l-operator-demo



Built in a garage, funded by pre-orders, no VC. Now we’re scaling to 1 k installer units.

We’re giving 50 limited-edition prototypes to investors , installers & researchers who want to co-design the sovereign smart home.

👇 Drop “EUSKERA” in the comments if you want an invite, tag a friend who still thinks Alexa is “convenient,” and smash ♥️ if AI should belong to people - not servers.
hesamation 
posted an update about 2 months ago
view post
Post
9195
a senior engineer at google just dropped a 400-page free book on docs for review: agentic design patterns.

the table of contents looks like everything you need to know about agents + code:
> advanced prompt techniques
> multi-agent patterns
> tool use and MCP
> you name it

read it here: https://docs.google.com/document/d/1rsaK53T3Lg5KoGwvf8ukOUvbELRtH-V0LnOIFDxBryE/edit?tab=t.0#heading=h.pxcur8v2qagu

you can also pre-order on Amazon (published by Springer) and the royalties goes to Save the Children: https://www.amazon.com/Agentic-Design-Patterns-Hands-Intelligent/dp/3032014018/
Tonic 
posted an update about 2 months ago
view post
Post
668
🙋🏻‍♂️ Hey there folks ,

Just wanted to annouce 🏭SmolFactory : it's the quickest and best way to finetune SmolLM3 and GPT-OSS-20B on huggingface !

Basicaly it's an app you can run on huggingface by duplicating the space and running your training directly on huggingface GPUs .

It will help you basically select datasets and models, fine tune your model , make an experiment tracker you can use on your mobile phone , push all your model card and even automatically make a demo for you on huggingface so you can directly test it out when it's done !

check out the blog to learn more : https://huggingface.co/blog/Tonic/smolfactory

or just try the app directly :
Tonic/SmolFactory

you can vibe check the cool models I made :
French SmolLM3 : Tonic/Petite-LLM-3
Medical GPT-OSS : Tonic/med-gpt-oss-20b-demo

check out the model cards :
multilingual reasoner (gpt-oss) - Tonic/gpt-oss-20b-multilingual-reasoner
med-gpt-oss : Tonic/med-gpt-oss-20b
petite-elle-l-aime : Tonic/petite-elle-L-aime-3-sft

github repo if you like command line more than gradio : https://github.com/josephrp/smolfactory

drop some likes on these links it's really much appreciated !

feedback and PRs are welcome !
Tonic 
posted an update 3 months ago
hesamation 
posted an update 3 months ago
view post
Post
4001
longer context doesn't generate better responses. it can even hurt your llm/agent. 1M context window doesn't automatically make models smarter as it's not about the size; it's how you use it.

here are 4 types of context failure and why each one happens:

1. context poisoning: if hallucination finds its way into your context, the agent will rely on that false information to make its future moves. for example if the agent hallucinates about the "task description", all of its planning to solve the task would also be corrupt.

2. context distraction: when the context becomes too bloated, the model focuses too much on it rather than come up with novel ideas or to follow what it has learned during training. as Gemini 2.5 Pro technical report points out, as context grows significantly from 100K tokens, "the agent showed a tendency toward favoring repeating actions from its vast history rather than synthesizing novel plans".

3. context confusion: everyone lost it when MCPs became popular, it seemed like AGI was achieved. I suspected there is something wrong and there was: it's not just about providing tools, bloating the context with tool use derails the model from selecting the right one! even if you can fit all your tool metadata in the context, as their number grows, the model gets confused over which one to pick.

4. Context Clash: if you exchange conversation with a model step by step and provide information as you go along, chances are you get worse performance rather than providing all the useful information at once. one the model's context fills with wrong information, it's more difficult to guide it to embrace the right info. agents pull information from tools, documents, user queries, etc. and there is a chance that some of these information contradict each other, and it's not good new for agentic applications.

check this article by Drew Breunig for deeper read: https://www.dbreunig.com/2025/06/26/how-to-fix-your-context.html?ref=blog.langchain.com
  • 2 replies
·
Tonic 
posted an update 3 months ago
view post
Post
805
👋 Hey there folks,

just submitted my plugin idea to the G-Assist Plugin Hackathon by @nvidia . Check it out, it's a great way to use a local SLA model on a windows machine to easily and locally get things done ! https://github.com/NVIDIA/G-Assist
Tonic 
posted an update 3 months ago
view post
Post
624
🙋🏻‍♂️ Hey there folks ,

Yesterday , Nvidia released a reasoning model that beats o3 on science, math and coding !

Today you can try it out here : Tonic/Nvidia-OpenReasoning

hope you like it !
Tonic 
posted an update 4 months ago
view post
Post
3377
🙋🏻‍♂️ Normalize adding compute & runtime traces to your model cards
  • 2 replies
·
hesamation 
posted an update 4 months ago
view post
Post
5356
in case you didn’t know, Claude now has a developer training course with certificates,

this is better than anything you can find on Coursera.

covers Claude Code, MCP and its advanced topics and even more:

https://www.anthropic.com/learn/build-with-claude
Tonic 
posted an update 4 months ago
view post
Post
534
Who's going to Raise Summit in Paris Tomorrow ?

If you're around , I would love to meet you :-)
hesamation 
posted an update 5 months ago
Tonic 
posted an update 5 months ago
view post
Post
709
🙋🏻‍♂️ hey there folks ,

So every bio/med/chem meeting i go to i always the same questions "why are you sharing a gdrive link with me for this?" and "Do you have any plans to publish your model weights and datasets on huggingface?" and finally i got a good answer today which explains everything :

basically there is some kind of government censorship on this (usa, but i'm sure others too) and they are told they are not allowed as it is considered a "dataleak" which is illegal !!!!

this is terrible ! but the good news is that we can do something about it !

so there is this "call for opinions and comments" here from the NIH (usa) , and here we can make our opinion on this topic known : https://osp.od.nih.gov/comment-form-responsibly-developing-and-sharing-generative-artificial-intelligence-tools-using-nih-controlled-access-data/

kindly consider dropping your opinion and thoughts about this censorship of science , and share this post , link or thoughts widely .

Together maybe we can start to share data and model weights appropriately and openly in a good way 🙏🏻🚀

cc. @cyrilzakka

hesamation 
posted an update 5 months ago
view post
Post
2786
I really like how this seven-stage pipeline was laid out in the Ultimate Guide to Fine-Tuning book.

It gives an overview, then goes into detail for each stage, even providing best practices.

It’s 115 pages on arxiv, definitely worth a read.

Check it out: https://arxiv.org/abs/2408.13296
Tonic 
posted an update 5 months ago
view post
Post
2561
🙋🏻‍♂️ Hey there folks ,

Yesterday the world's first "Learn to Vibe Code" application was released .

As vibe coding is the mainstream paradigm , so now the first educational app is there to support it .

You can try it out already :

https://vibe.takara.ai

and of course it's entirely open source, so i already made my issue and feature branch :-) 🚀