Hugging Face's logo

Keras Dreambooth Event
community
Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

MElHuseyni  authored a paper 8 days ago
Doppler-Enhanced Deep Learning: Improving Thyroid Nodule Segmentation with YOLOv5 Instance Segmentation
MElHuseyni  authored a paper 16 days ago
Parrot: Persuasion and Agreement Robustness Rating of Output Truth -- A Sycophancy Robustness Benchmark for LLMs
MElHuseyni  authored a paper 19 days ago
TurkColBERT: A Benchmark of Dense and Late-Interaction Models for Turkish Information Retrieval
View all activity

Aurelien-Morgan 
posted an update about 4 hours ago
lunarflu 
posted an update about 1 month ago
lunarflu 
posted an update about 1 month ago
lunarflu 
posted an update about 1 month ago
view post
Post
2674
💸🤑You don’t need 100 GPUs to train something amazing!

Our Smol Training Playbook teaches you a better path to world-class LLMs, for free!

Check out the #1 trending space on 🤗 :
HuggingFaceTB/smol-training-playbook
sayakpaul 
authored a paper 2 months ago
lunarflu 
posted an update 2 months ago
view post
Post
2269
Cool stuff these past weeks on huggingface! 🤗 🚀 !
• 📈Trackio, local-first W&B alternative
https://github.com/gradio-app/trackio/issues
• 🌍EmbeddingGemma, 300M-param, multilingual embeddings, on-device
https://huggingface.co/blog/embeddinggemma
• 💻Open LLMs in VS Code (Inference Providers)
https://x.com/reach_vb/status/1966185427582497171
• 🤖Smol2Operator GUI agents
https://huggingface.co/blog/smol2operator
• 🖼️Gradio visible watermarking
https://huggingface.co/blog/watermarking-with-gradio
rishiraj 
authored a paper 3 months ago
kadirnar 
posted an update 4 months ago
view post
Post
2325
What can you do with the VyvoTTS library?

- You can train a model in a language it has never been trained in using the PT model. There’s no need for large datasets.
- With the PT model, you can easily replicate the voice of any character you want. Just 1k samples are enough.
- You can add emotion support with a small dataset.

Github: https://github.com/Vyvo-Labs/VyvoTTS
HuggingFace: Vyvo
sayakpaul 
posted an update 5 months ago
view post
Post
1921
Fast LoRA inference for Flux with Diffusers and PEFT 🚨

There are great materials that demonstrate how to optimize inference for popular image generation models, such as Flux. However, very few cover how to serve LoRAs fast, despite LoRAs being an inseparable part of their adoption.

In our latest post, @BenjaminB and I show different techniques to optimize LoRA inference for the Flux family of models for image generation. Our recipe includes the use of:

1. torch.compile
2. Flash Attention 3 (when compatible)
3. Dynamic FP8 weight quantization (when compatible)
4. Hotswapping for avoiding recompilation during swapping new LoRAs 🤯

We have tested our recipe with Flux.1-Dev on both H100 and RTX 4090. We achieve at least a *2x speedup* in either of the GPUs. We believe our recipe is grounded in the reality of how LoRA-based use cases are generally served. So, we hope this will be beneficial to the community 🤗

Even though our recipe was tested primarily with NVIDIA GPUs, it should also work with AMD GPUs.

Learn the details and the full code here:
https://huggingface.co/blog/lora-fast
juancopi81 
updated a Space 5 months ago
sayakpaul 
posted an update 7 months ago
view post
Post
2911
Diffusers supports a good variety of quantization backends. It can be challenging to navigate through them, given the complex nature of diffusion pipelines in general.

So, @derekl35 set out to write a comprehensive guide that puts users in the front seat. Explore the different backends we support, learn the trade-offs they offer, and finally, check out the cool space we built that lets you compare quantization results.

Give it a go here:
https://lnkd.in/gf8Pi4-2
  • 2 replies
·
sayakpaul 
posted an update 7 months ago
view post
Post
1848
Despite the emergence of combining LLM and DiT architectures for T2I synthesis, its design remains severely understudied.

This was done long ago and got into CVPR25 -- super excited to finally share it now, along with the data and code ♥️

We explore several architectural choices that affect this design. We provide an open & reproducible training recipe that works at scale.

Works like Playground v3 have already explored a deep fusion between an LLM and a DiT, sharing their representations through layerwise attention. They exhibit excellent performance on T2I.

Despite its compelling results and other performance virtues, it remains unexplored, which is what we want to improve in our work. Specifically, we take a pre-trained LLM (Gemma-2B) and trainable DiT, and set out to explore what makes a "good deep fusion" between the two for T2I.

We explore several key questions in the work, such as:

Q1: How should we do attention? We considered several alternatives. PixArt-Alpha like attention (cross-attention) is very promising.
Q2: Should we incorporate additional text modulation?
Q3: Can we eliminate timestep conditioning?
Q4: How do we do positional encodings?
Q5: Do instruction-tuned LLMs help deep fusion?
Q6: Would using a decoder LLM from a multimodal model be helpful?
Q7: Does using a better variant of Gemma help?

Based on the above findings, we arrive at FuseDiT with the following components on top of the base architecture from the findings of our experiments.

* No AdaLN-Zero modules
* 1D + 2D-RoPE
* Gemma 2 2B, adjusting DiT configurations accordingly

We trained FuseDiT on a mixture from CC12M, JourneyDB, & SA (~26M image-text pairs) for 800 steps. While not the best model, it's encouraging to develop something in a guided manner using open datasets.

To know more (code, models, all are available), please check out the paper:
https://lnkd.in/gg6qyqZX.
sayakpaul 
authored a paper 7 months ago
Aurelien-Morgan 
posted an update 7 months ago
shivalikasingh 
authored a paper 7 months ago
Aurelien-Morgan 
posted an update 8 months ago
view post
Post
3156
The Almighty function-caller

How would you like to build smart GenAi infrastructure ?
Give extensive tools memory to your edge agentic system,
And optimize the resources it takes to run yet a high-performance set of agents ?

We came up with a novel approach to function-calling at scale for smart companies and corporate-grade use-cases.

Read our full-fledged blog article on this here on Hugging Face :
https://huggingface.co/blog/Aurelien-Morgan/the-almighty-function-caller
Aurelien-Morgan 
posted an update 8 months ago
view post
Post
677
retrain-pipelines 0.1.2 finally dropped. It comes with a hot Hugging Face Hub integration. Go check it out. We have 2 articles about it coming up. One already fully written so, be on the lookout !
@retrain-pipelines

Also, I'll be volunteering at GOSIM AI Paris 2025. If you're interested in chatting, hmu.
sayakpaul 
authored a paper 8 months ago
Aurelien-Morgan 
posted an update 9 months ago
sayakpaul 
authored a paper 9 months ago