Hugging Face's logo

Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up

All HF Hub posts
pagezyhfΒ 
posted an update 2 days ago
view post
Post
2757
🀝 Collaborating with AMD to ensure Hugging Face Transformers runs smoothly on AMD GPUs!

We run daily CI on AMD MI325 to track the health of the most important model architectures and we’ve just made our internal dashboard public.

By making this easily accessible, we hope to spark community contributions and improve support for everyone!
  • 2 replies
Β·
vansinΒ 
posted an update 2 days ago
view post
Post
1902
A cute Intern With Hugging Face
sergiopaniegoΒ 
posted an update 3 days ago
view post
Post
3783
gpt-oss was possible thanks to new engineering efforts in πŸ€— transformers. We just dropped a blog covering them:

- Kernels from the Hub
- MXFP4 Quantization
- Tensor & Expert Parallelism
- Dynamic Sliding Window & Cache
- Continuous Batching & Paged Attention

Grab a coffee & dive in! β˜•οΈ

https://huggingface.co/blog/faster-transformers
yjerniteΒ 
posted an update 3 days ago
view post
Post
1899
Tremendous quality of life upgrade on the Hugging Face Hub - we now have auto-complete emojis πŸ€— πŸ₯³ πŸ‘ πŸ™Œ πŸŽ‰

Get ready for lots more very serious analysis on a whole range of topics from yours truly now that we have unlocked this full range of expression πŸ˜„ πŸ€” πŸ—£ πŸ™Š
prithivMLmodsΒ 
posted an update about 21 hours ago
view post
Post
1177
Introducing Gliese-OCR-7B-Post1.0, a document content-structure retrieval VLM designed for content extraction(OCRs) and summarization. This is the third model in the Camel Doc OCR VLM series, following Camel-Doc-OCR-062825. The new version fixes formal table reconstruction issues in both En and Zh, achieving optimal performance for long-context inferences. This model also shows significant improvements in LaTeX and Markdown rendering for OCR tasks.

πŸ€— Gliese-OCR-7B-Post1.0 : prithivMLmods/Gliese-OCR-7B-Post1.0
✨ Demo Space/App : prithivMLmods/Multimodal-VLM-v1.0
πŸ“Œ Gliese-Post1.0 Collection : prithivMLmods/gliese-post10-68c52c4a6ca4935f5259a6d7
⬅️ Previous Versions : prithivMLmods/Camel-Doc-OCR-062825
🧨 Gliese-OCR-7B-Post1.0 (4-bit) Notebook Demo on T4 : prithivMLmods/Gliese-OCR-7B-Post1.0
πŸ“– GitHub [Gliese-OCR-7B-Post1.0(4-bit)-reportlab] : https://tinyurl.com/ys7zuerc

Other Collections:

βž” Multimodal Implementations : prithivMLmods/multimodal-implementations-67c9982ea04b39f0608badb0
βž” Multimodal VLMs - Aug'25 : prithivMLmods/multimodal-vlms-aug25-68a56aac39fe8084f3c168bd
βž” Multimodal VLMs - July'25 : prithivMLmods/multimodal-vlms-until-july25-688312e6b840e1e156f13027

.
.
.
To know more about it, visit the app page or the respective model page!!
DualityAI-RebekahBogdanoffΒ 
posted an update 1 day ago
view post
Post
2201
πŸŽ‰ Big congratulations to the winners of the "Synthetic 2 Real Object Detection Challenge 2", the second Kaggle challenge that Duality AI hosted. This competition was more fierce than the last one, but these users managed to clench the win!

πŸ₯‡ 1st place: @sergio-sanz-rodriguez (see the blog he produced with us outlining how he achieved his results: https://tinyurl.com/mreunr98)

πŸ₯ˆ 2nd place: Kaggle user Diana Shilova - https://tinyurl.com/yjjz3szm

πŸ₯‰ 3rd place: Kaggle user ηœ‰ι—΄ε°Ί - https://tinyurl.com/ycxskfzv

View the entire leaderboard at - https://tinyurl.com/jm2ery7w

Join our current Multi-Class Object Detection Synthetic2Real Kaggle competition here: https://tinyurl.com/y224rttu

And we will soon be launching a new competition in a new domain! Hint: πŸŒ„ 🏠 🌳 ✈️
salma-remyxΒ 
posted an update 2 days ago
view post
Post
3905
Most apps don't have great full-text search over their assets.

We've developed an agent to automate the environment building and testing of experimental codebases sourced from arXiv. We push these containerized reproductions daily to Docker Hub: https://hub.docker.com/u/remyxai

However, searching for them can be challenging unless you know the specific arXiv ID associated with each paper.

We are currently working on implementing a search feature in Remyx, which will make these assets easily discoverable and ready for testing πŸ” Stay tuned!

Discover your next best idea to experiment with here: https://engine.remyx.ai
JawardΒ 
posted an update 1 day ago
ArturoNereuΒ 
posted an update 1 day ago
view post
Post
639
I like the direction that Claude Code took in visualizing context usage. As these tools are being built, I think the work now needs to focus on control over how to clean up, inspect, and profile. Renderdoc-like maybe?
ehristoforuΒ 
posted an update 1 day ago
view post
Post
1121
πŸš€Hello from the Project Fluently team!

✨ We are happy to share with you our new universal LLM models based on Qwen3 1.7B and 4B β€” powerful, multilingual and ready to solve a wide range of problems!

πŸ› οΈ We have conducted additional training and carefully merged them to achieve even better results and maximize the potential of the models.

πŸ†“ And most importantly β€” the models are completely open and free under the Apache-2.0 license!

πŸ”— Links to repositories:
- FluentlyQwen3-4B: fluently/FluentlyQwen3-4B
- FluentlyQwen3-1.7B: fluently/FluentlyQwen3-1.7B

😍 We will be very glad to hear your feedback and impressions! Your opinion is very important to us!
Recently active users