Hugging Face's logo

Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up

All HF Hub posts
danielhanchen 
posted an update 2 days ago
mayafree 
posted an update 1 day ago
view post
Post
2101
I built a Space that lets you switch between all three Qwen3.5 official collection models in a single interface.

MAYA-AI/QWEN-3_5-CHAT

The architecture is the key part. Instead of using Gradio as the UI, I use it purely as an API engine. FastAPI serves a fully custom HTML/JS frontend that calls /gradio_api/call/chat via SSE streaming. No DOM conflicts, no layout constraints.

Four main features: instant model switching with automatic spec adjustment (max tokens, temperature ceiling, Vision availability all update per model), Thinking Mode via /think prefix with collapsible reasoning chain, Vision image upload via base64 conversion, and HF OAuth implemented directly at the FastAPI level.

For model selection: 122B-A10B with Thinking Mode for math, logic, and agents. 27B for writing, translation, and instruction following. 35B-A3B for fast everyday questions.

A few surprises during development — Gradio 6.x removed several parameters quietly, base64 image strings broke gr.Image(type="pil") so I switched to gr.Textbox with backend PIL conversion, and Thinking Mode parsing needed a full rewrite with indexOf instead of regex.

Thanks to the Qwen team for making this possible. Try it out and let me know what you think.

#Qwen3 #Qwen35 #OpenSourceAI #HuggingFace #LLM #ThinkingAI #vidraft #MultimodalAI
SeaWolf-AI 
posted an update about 12 hours ago
view post
Post
866
ALL Bench — Global AI Model Unified Leaderboard

FINAL-Bench/all-bench-leaderboard

If you've ever tried to compare GPT-5.2 and Claude Opus 4.6 side by side, you've probably hit the same wall: the official Hugging Face leaderboard only tracks open-source models, so the most widely used AI systems simply aren't there. ALL Bench fixes that by bringing closed-source models, open-weight models, and — uniquely — all four teams under South Korea's national sovereign AI program into a single leaderboard. Thirty-one frontier models, one consistent scoring scale.
Scoring works differently here too. Most leaderboards skip benchmarks a model hasn't submitted, which lets models game their ranking by withholding results. ALL Bench treats every missing entry as zero and divides by ten, so there's no advantage in hiding your weak spots.
The ten core benchmarks span reasoning (GPQA Diamond, AIME 2025, HLE, ARC-AGI-2), coding (SWE-bench Verified, LiveCodeBench), and instruction-following (IFEval, BFCL). The standout is FINAL Bench — the world's only benchmark measuring whether a model can catch and correct its own mistakes. It reached rank five in global dataset popularity on Hugging Face in February 2026 and has been covered by Seoul Shinmun, Asia Economy, IT Chosun, and Behind.
Nine interactive charts let you explore everything from composite score rankings and a full heatmap to an open-vs-closed scatter plot. Operational metrics like context window, output speed, and pricing are included alongside benchmark scores.
All data is sourced from Artificial Analysis Intelligence Index v4.0, arXiv technical reports, Chatbot Arena ELO ratings, and the Korean Ministry of Science and ICT's official evaluation results. Updates monthly.
OzTianlu 
posted an update 3 days ago
view post
Post
4684
🔥 UPGRADE in Kai: 30B Scaling! 🔥
NoesisLab/Kai-30B-Instruct
NoesisLab/Kai-3B-Instruct
We are incredibly excited to announce that the Kai-30B-Instruct model and its official Space are now LIVE! 🚀
If you've been following the journey from Kai-0.35B to Kai-3B, you know we're rethinking how models reason. Tired of verbose, slow Chain-of-Thought (CoT) outputs that flood your screen with self-talk? So are we.
Kai-30B-Instruct scales up our Adaptive Dual-Search Distillation (ADS) framework. By bridging classical A* heuristic search with continuous gradient descent , we use an information-theoretic log-barrier to physically prune high-entropy reasoning paths during training.
The result? Pure implicit reasoning. The model executes structured logic, arithmetic carries, and branch selections as a reflex in a single forward pass—no external scaffolding required.
At 3B, we observed a phase transition where the model achieved "logical crystallization". Now, at 30B, we are giving the ADS regularizer the massive representational capacity it needs to tackle higher-order symbolic abstractions and complex reasoning tasks.
🧪 Test Kai yourself in our new Space:
NoesisLab/Kai-3B-Instruct
📦 Model Weights:
NoesisLab/Kai-30B-Instruct
Bring your hardest math, logic, and coding benchmarks. We invite the community to stress-test the limits of the penalty wall! 🧱💥
  • 1 reply
·
appvoid 
posted an update 2 days ago
view post
Post
2271
Let's keep the momentum for small models. I just published dot. It's the first pretrained causal model that is trained on math/symbols rather than english. The goal is to get an agnostic fewshot meta learner that learns from reality itself instead of language.

It's already decent at some tasks, with next version coming in a few weeks.


appvoid/dot
·
hannayukhymenko 
posted an update 3 days ago
view post
Post
1752
Do you translate your benchmarks from English correctly? 🤔
Turns out, for many languages it is much harder than you can imagine!

Introducing Recovered in Translation 🌍 together with @aalexandrov
ritranslation.insait.ai

Translating benchmarks is a painful process, requiring a lot of manual inspection and adjustments. You start from setting up the whole pipeline and adapting to every format type, including task specifics. There already exist some massive benchmarks, but they still have some simple (and sometimes silly) bugs, which can hurt the evaluations :( We present a novel automated translation framework to help with that!

Eastern and Southern European languages introduce richer linguistic structures compared to English and for benchmarks which heavily rely on grammatical coherence machine translation presents a risk of harming evaluations. We discover potential answer leakage or misleading through grammatical structure of the questions. Some benchmarks are also just outdated and need to be retranslated with newer and better models.

We present a framework with novel test-time scaling methods which allow to control time and cost investments, while at the same time mitigate the need for human-in-the-loop verification. While working on Ukrainian-focused MamayLM models, we had to translate 10+ benchmarks in a short span of time. Finding human evaluators is costly and time-consuming, same goes for using professional translators. With our pipeline we were able to do it in 3 days🏎️

We hope our findings will help enable stronger multilingual evaluations and developments. We release all produced benchmarks on Hugging Face together with the source code and Arxiv paper 🤗

Paper: Recovered in Translation: Efficient Pipeline for Automated Translation of Benchmarks and Datasets (2602.22207)
Code: https://github.com/insait-institute/ritranslation
Benchmarks: https://huggingface.co/collections/INSAIT-Institute/multilingual-benchmarks
  • 1 reply
·
NJX-njx 
posted an update 3 days ago
view post
Post
7351
Recently, I have open-sourced an AI emotional companion product based on openclaw, called opensoul.

On this platform, you can create a "soulmate" that matches your personality, and configure it with the skills, tools you want it to have, as well as the platforms it can integrate with (such as Telegram, Discord, etc.).
You can even create group chats, invite multiple agents and your friends to chat about recent events, discuss projects together, and so on.

On the one hand, I hope it can better accompany you in daily life by virtue of its unique memory mechanism, self-feedback and iteration mechanism, and the modeling of users' emotions. On the other hand, I also hope it can help you better handle your work with its unique skills, tools and ability to deal with complex task scenarios.

Although the entire product has taken shape, I think there are still many areas that need adjustment and optimization. I also hope to rely on the strength of the community to do a good job in AI emotional companionship.

This is the project introduction URL: https://opensoul-web.vercel.app
This is the GitHub project URL: https://github.com/NJX-njx/opensoul
@AdinaY @lilianweng@burtenshaw@clem
let's just do it

·
prithivMLmods 
posted an update 1 day ago
view post
Post
2858
QIE-Object-Remover-Bbox Demo removes objects and artifacts from selected regions using bounding box grounding. Built on Qwen-Image-Edit-2509 with Rapid Diffusers acceleration, it delivers fast 4-step inference via the QIE-2509 adapter. 🤗🔥

🔗Demo Space: prithivMLmods/QIE-Object-Remover-Bbox
🔗Qwen-Image-Edit-Rapid-AIO: prithivMLmods/Qwen-Image-Edit-Rapid-AIO-V4
🔗Adapter-(LoRA): prithivMLmods/QIE-2509-Object-Remover-Bbox

🔗Collection: https://huggingface.co/collections/prithivMLmods/qwen-image-edit-layout-bbox

To learn more, visit the app page or the respective model pages.
nightmedia 
posted an update 2 days ago
view post
Post
1628
Qwen3.5 Performance Metrics

With the 3.5 architecture, a lot of the old quanting methods don't work as before. I noticed this when benchmarking Deckard(qx) quants and by mistake ran a q8 that was better. That only happens if the qx sucked--and it did--enhancing layers just because they look interesting doesn't work anymore, so until I get a clear understanding of the architecture, I will publish mxfp4 and mxfp8 of the 3.5 models, that seem very stable and high performant

I will start posting here the metrics I gather from the series, starting with the smallest. If I have numbers from previous or similar models, I will post them in comparison

Qwen3.5-0.8B

quant    arc   arc/e boolq hswag obkqa piqa  wino
mxfp8    0.351,0.501,0.733,0.462,0.348,0.682,0.573
mxfp4    0.339,0.489,0.738,0.433,0.330,0.672,0.553

Old model performance

Qwen3-0.6B
bf16     0.298,0.354,0.378,0.415,0.344,0.649,0.534
q8-hi    0.296,0.355,0.378,0.416,0.348,0.652,0.529
q8       0.299,0.354,0.378,0.414,0.346,0.650,0.535
q6-hi    0.301,0.356,0.378,0.415,0.350,0.651,0.541
q6       0.300,0.367,0.378,0.416,0.344,0.647,0.524
mxfp4    0.286,0.364,0.609,0.404,0.316,0.626,0.531

Quant    Perplexity     Peak memory
mxfp8    6.611 ± 0.049  7.65 GB
mxfp4    7.455 ± 0.057  6.33 GB


Detailed metrics by model

nightmedia/Qwen3.5-0.8B-mxfp8-mlx

nightmedia/Qwen3.5-2B-mxfp8-mlx

nightmedia/Qwen3.5-4B-mxfp8-mlx

nightmedia/Qwen3.5-9B-mxfp8-mlx

nightmedia/Qwen3.5-27B-Text

nightmedia/Qwen3.5-122B-A10B-Text-mxfp4-mlx

More metrics coming soon.

I am running these on my Mac, an M4Max with 128GB RAM. Some performance numbers like tokens/second reflect the performance on my box.

This post will be updated with every model that gets tested. The larger models take hours, the 27B a couple days, so it will be a long process.

-G
·
MaziyarPanahi 
posted an update about 20 hours ago
view post
Post
816
DNA, mRNA, proteins, AI. I spent the last year going deep into computational biology as an ML engineer. This is Part I of what I found. 🧬

In 2024, AlphaFold won the Nobel Prize in Chemistry.

By 2026, the open-source community had built alternatives that outperform it.

That's the story I find most interesting about protein AI right now. Not just the science (which is incredible), but the speed at which open-source caught up. Multiple teams, independently, reproduced and then exceeded AlphaFold 3's accuracy with permissive licenses. The field went from prediction to generation: we're not just modeling known proteins anymore, we're designing new ones.

I spent months mapping this landscape for ML engineers. What the architectures actually are (spoiler: transformers and diffusion models), which tools to use for what, and which ones you can actually ship commercially.

New post on the Hugging Face blog: https://huggingface.co/blog/MaziyarPanahi/protein-ai-landscape

Hope you all enjoy! 🤗
Recently active users