Hugging Face's logo

Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up

All HF Hub posts
NymboΒ 
posted an update 3 days ago
view post
Post
5879
We should really have a release date range slider on the /models page. Tired of "trending/most downloaded" being the best way to sort and still seeing models from 2023 on the first page just because they're embedded in enterprise pipelines and get downloaded repeatedly. "Recently Created/Recently Updated" don't solve the discovery problem considering the amount of noise to sift through.

Slight caveat: Trending actually does have some recency bias, but it's not strong/precise enough.
Β·
danielhanchenΒ 
posted an update about 17 hours ago
view post
Post
823
Introducing Unsloth Studio ✨
A new open-source web UI to train and run LLMs.

β€’ Run models locally on Mac, Windows, Linux
β€’ Train 500+ models 2x faster with 70% less VRAM
β€’ Supports GGUF, vision, audio, embedding models
β€’ Auto-create datasets from PDF, CSV, DOCX
β€’ Self-healing tool calling and code execution
β€’ Compare models side by side + export to GGUF

GitHub: https://github.com/unslothai/unsloth
Blog and Guide: https://unsloth.ai/docs/new/studio

Available now on Hugging Face, NVIDIA, Docker and Colab.
unmodeled-tylerΒ 
posted an update 2 days ago
view post
Post
5633
LINK: https://github.com/unmodeled-tyler/vessel-browser

Hey Hugging Face!

It's been quiet from me over here for the last few weeks, but I've been busy building! I just submitted my project to the Hermes Agent Hackathon, and wanted to share it with all of you.

This is Vessel Browser - an AI-native web browser that runs locally on Linux, and is operated by your personal AI agent via MCP server. Vessel is built from the ground up around the agent as first-class and visible UI for human-in-the-loop with 3 different levels of permissions.

Your agent finds, reads, and organizes the web for you, based on what you actually care about - not what a platform's algorithm thinks you care about.

Once your agent finds what it's looking for, it can organize bookmarked pages into custom folders with summaries for later browsing, take screenshots with highlighted text, and integrate with Obsidian for long-term browsing related-memory.

Check it out!
Β·
Keeby-smilyaiΒ 
posted an update about 11 hours ago
view post
Post
698
Hello everyone!
robtacconelliΒ 
posted an update 1 day ago
view post
Post
3181
🧬 Midicoth: diffusion-based lossless compression β€” no neural net, no GPU, no training data

What if reverse diffusion could compress text β€” without a neural network?
Midicoth brings score-based denoising into classical compression. It treats prior smoothing as forward noise and reverses it with Tweedie's formula on a binary tree β€” 3 denoising steps, James-Stein shrinkage, applied after all model blending. ~2,000 lines of C, single CPU core.

Beats every dictionary compressor we tested:
enwik8 (100 MB) β†’ 1.753 bpb (βˆ’11.9% vs xz, βˆ’15% vs Brotli, βˆ’24.5% vs bzip2)
alice29.txt β†’ 2.119 bpb (βˆ’16.9% vs xz)
Outperforms xz, zstd, Brotli, bzip2, gzip on all inputs

PAQ/CMIX still win with hundreds of models + LSTMs. LLM compressors win with pre-trained knowledge. Midicoth closes the gap with pure statistics β€” no mixer, no gradient descent, just counting.
The Tweedie denoising layer adds 2.3–2.7% on every file tested β€” the most consistent component in the ablation. Adding SSE or logistic mixers made things worse. In the online setting, count-based beats gradient-based.
No external dependencies. Fully deterministic. Bit-exact encode/decode. ~60 KB/s throughput.
πŸ’» Code: https://github.com/robtacconelli/midicoth
πŸ“„ Paper: Micro-Diffusion Compression -- Binary Tree Tweedie Denoising for Online Probability Estimation (2603.08771)
⭐ Space: robtacconelli/midicoth

If you ever wondered whether diffusion ideas belong in data compression β€” here's proof they do. ⭐ appreciated!
prithivMLmodsΒ 
posted an update about 19 hours ago
view post
Post
897
Introducing QIE-Bbox-Studio! πŸ”₯πŸ€—

The QIE-Bbox-Studio demo is now live β€” more precise and packed with more options. Users can manipulate images with object removal, design addition, and even move objects from one place to another, all in just 4-step fast inference.

πŸ€— Demo: prithivMLmods/QIE-Bbox-Studio
πŸ”— GitHub: https://github.com/PRITHIVSAKTHIUR/QIE-Bbox-Studio

πŸš€ Models [LoRA] :

● QIE-2511-Object-Mover-Bbox: prithivMLmods/QIE-2511-Object-Mover-Bbox
● QIE-2511-Object-Remover-Bbox-v3: prithivMLmods/QIE-2511-Object-Remover-Bbox-v3
● QIE-2511-Outfit-Design-Layout: prithivMLmods/QIE-2511-Outfit-Design-Layout
● QIE-2509-Object-Remover-Bbox-v3: prithivMLmods/QIE-2509-Object-Remover-Bbox-v3
● QIE-2509-Object-Mover-Bbox: prithivMLmods/QIE-2509-Object-Mover-Bbox

πŸš€ Collection:

● Qwen Image Edit [Layout Bbox]: https://huggingface.co/collections/prithivMLmods/qwen-image-edit-layout-bbox

To learn more, visit the app page or the respective model pages.
W8YiΒ 
posted an update 2 days ago
view post
Post
2631
I built a TCGA WSI feature dataset using UNI2-h.

The official release currently has incomplete coverage (see discussion):
MahmoodLab/UNI2-h-features#2

To make the features easier to use for research, I generated a new dataset:

W8Yi/tcga-wsi-uni2h-features

Key differences from the official release:

β€’ All detected tissue tiles are encoded (not a sampled subset)
β€’ Features can be downloaded per slide instead of large ZIP archives
β€’ QC overlay images are provided for visual inspection
β€’ UNI2-h 1536-D tile embeddings stored in H5 format
β€’ Organized by TCGA project for easier use in MIL / retrieval pipelines

Example layout:

TCGA-HNSC/
  features/*.h5
  vis/*__overlay.png


Hope this helps others working on computational pathology and TCGA WSI research.
OzTianluΒ 
posted an update 3 days ago
view post
Post
5301
Arcade-3B β€” SmolReasoner
NoesisLab/Arcade-3B
Arcade-3B is a 3B instruction-following and reasoning model built on SmolLM3-3B. It is the public release from the ARCADE project at NoesisLab, which investigates the State–Constraint Orthogonality Hypothesis: standard Transformer hidden states conflate factual content and reasoning structure in the same subspace, and explicitly decoupling them improves generalization.
  • 5 replies
Β·
prithivMLmodsΒ 
posted an update 4 days ago
view post
Post
4934
QIE-2509-Object-Remover-Bbox-v3 is a more stable version of the Qwen Image Edit visual grounding–based object removal model. The app was previously featured in HF Spaces of the Week and is now updated with the latest Bbox-v3 LoRA adapter.

πŸ€— Demo: prithivMLmods/QIE-Object-Remover-Bbox
πŸ€— LoRA: prithivMLmods/QIE-2509-Object-Remover-Bbox-v3
πŸ€— Collection: https://huggingface.co/collections/prithivMLmods/qwen-image-edit-layout-bbox

To learn more, visit the app page or the respective model pages.
  • 2 replies
Β·
DedeProGamesΒ 
posted an update about 15 hours ago
view post
Post
680
Introducing GRM Family, a family of fine-tuned small models from the Qwen2.5 family for Long Cot and General Reasoning and Agentic Tasks.

GRM is available in 7b and 1.5b parameter sizes, these models being significantly relevant for complex tasks or local inference agents.
OrionLLM/GRM-7b
OrionLLM/GRM-1.5b
Recently active users