Hugging Face – Posts

Join the conversation

Join the community of Machine Learners and AI enthusiasts.

All HF Hub posts

openfree

posted an update 1 day ago

Post

3005

📚 Multilingual RAG Chatbot with PDF Support

Chat naturally with your documents! 🌟

✨ Key Features:
• 🌏 Multilingual Q&A support (English, Korean, etc.)
• 📄 Real-time PDF and text file processing
• 🔍 Context-aware accurate responses
• ⚡ Intuitive Chainlit-powered chat interface

🛠️ Tech Stack:
• 💻 Clean, documented open-source code
• 🤝 User-friendly Chainlit UI
• 📊 Vector database for efficient retrieval
• 🔄 Real-time streaming responses

📱 Try it now!
→ Demo: openfree/PDF-RAG

🔧 Special Features:
• 📊 Support for PDF/text files up to 2MB
• 🎯 Precise context understanding
• ⚡ Fast response time
• 🔒 Secure file handling

Full source code available - ready to integrate into your projects!

#RAG #NLP #Chatbot #OpenSource #PDFProcessing

hexgrad

posted an update about 12 hours ago

Post

1657

hexgrad/Kokoro-82M got an upgrade! ⬆️ More voices, more languages, pip install kokoro, and still 82M parameters.

GitHub: https://github.com/hexgrad/kokoro
PyPI: https://pypi.org/project/kokoro/

4 replies

prithivMLmods

posted an update 1 day ago

Post

2109

Deepswipe by
.
.
.
. Deepseek🐬🗿

Everything is now in recovery. 📉📈

2 replies

victor

posted an update 2 days ago

Post

2540

Finally, an open-source AI that turns your lyrics into full songs is here—meet YuE! Unlike other tools that only create short clips, YuE can make entire songs (up to 5 minutes) with vocals, melody, and instruments all working together. Letsss go!

m-a-p/YuE-s1-7B-anneal-en-cot

1 reply

dylanebert

posted an update 1 day ago

Post

2009

I made a 1 minute video explaining the DeepSeek situation

R1: deepseek-ai/DeepSeek-R1
Janus Pro: deepseek-ai/Janus-Pro-7B

3 replies

m-ric

posted an update 2 days ago

Post

2509

𝗧𝗵𝗲 𝗛𝘂𝗯 𝘄𝗲𝗹𝗰𝗼𝗺𝗲𝘀 𝗲𝘅𝘁𝗲𝗿𝗻𝗮𝗹 𝗶𝗻𝗳𝗲𝗿𝗲𝗻𝗰𝗲 𝗽𝗿𝗼𝘃𝗶𝗱𝗲𝗿𝘀!

✅ Hosting our own inference was not enough: now the Hub 4 new inference providers: fal, Replicate, SambaNova Systems, & Together AI.

Check model cards on the Hub: you can now, in 1 click, use inference from various providers (cf video demo)

Their inference can also be used through our Inference API client. There, you can use either your custom provider key, or your HF token, then billing will be handled directly on your HF account, as a way to centralize all expenses.

💸 Also, PRO users get 2$ inference credits per month!

Read more in the announcement 👉 https://huggingface.co/blog/inference-providers

1 reply

DualityAI-RebekahBogdanoff

posted an update about 15 hours ago

Post

677

🗣️💬We at Duality.ai want to hear about your specific dataset needs!!

We created a pose estimation dataset and an explanatory colab here:
➡️Dataset: duality-robotics/pose_estimation
➡️Colab: https://falcon.duality.ai/secure/documentation/pose-colab (you will have to create a free account to access)

😎We want to continue supporting the computer vision community, but we need to hear from you-
❓What computer vision tasks you are working on that could benefit from intentionally crafted data produced by our simulation software, FalconEditor?

Share your ideas in the comment section below, and we'll create annotated and labeled datasets to address the most pressing community needs.

Some areas to consider:

- Object detection in challenging environments
- Semantic segmentation for diverse scenes
- Pose Estimation data set with variance (IDK)
- Multi-object tracking
- Anomaly detection
- Domain-specific tasks (e.g., medical imaging, autonomous driving)

Let us know your dataset needs, and we'll work on generating synthetic data to address them!

As always, create a free EDU account to start using FalconEditor to create synthetic data on your own! Sign up here: https://falcon.duality.ai/auth/sign-up

mkurman

posted an update 1 day ago

Post

1495

Ok, my 14B DeepSeek R1 merge with Qwen2.5 1M is really hot right now—it's got 2.6k downloads! It's sitting pretty as the top trending model on the third page. 🔥

Check it out if you haven't already!
mkurman/Qwen2.5-14B-DeepSeek-R1-1M

11 replies

fdaudens

posted an update 3 days ago

Post

7283

Yes, DeepSeek R1's release is impressive. But the real story is what happened in just 7 days after:

- Original release: 8 models, 540K downloads. Just the beginning...

- The community turned those open-weight models into +550 NEW models on Hugging Face. Total downloads? 2.5M—nearly 5X the originals.

The reason? DeepSeek models are open-weight, letting anyone build on top of them. Interesting to note that the community focused on quantized versions for better efficiency & accessibility. They want models that use less memory, run faster, and are more energy-efficient.

When you empower builders, innovation explodes. For everyone. 🚀

The most popular community model? @bartowski 's DeepSeek-R1-Distill-Qwen-32B-GGUF version — 1M downloads alone.

4 replies

chansung

posted an update 2 days ago

Post

1571

Simple summary on DeepSeek AI's Janus-Pro: A fresh take on multimodal AI!

It builds on its predecessor, Janus, by tweaking the training methodology rather than the model architecture. The result? Improved performance in understanding and generating multimodal data.

Janus-Pro uses a three-stage training strategy, similar to Janus, but with key modifications:
✦ Stage 1 & 2: Focus on separate training for specific objectives, rather than mixing data.
✦ Stage 3: Fine-tuning with a careful balance of multimodal data.

Benchmarks show Janus-Pro holds its own against specialized models like TokenFlow XL and MetaMorph, and other multimodal models like SD3 Medium and DALL-E 3.

The main limitation? Low image resolution (384x384). However, this seems like a strategic choice to focus on establishing a solid "recipe" for multimodal models. Future work will likely leverage this recipe and increased computing power to achieve higher resolutions.

Recently active users