109 11 213

s3nh

AI & ML interests

Quantization, LLMs, Deep Learning for good. Follow me if you like my work. Patreon.com/s3nh

Recent Activity

upvoted a paper 4 days ago

A Rank Stabilization Scaling Factor for Fine-Tuning with LoRA

reacted to sayakpaul's post with 🔥 5 days ago

Commits speak louder than words 🤪 * 4 new video models * Multiple image models, including SANA & Flux Control * New quantizers -> GGUF & TorchAO * New training scripts Enjoy this holiday-special Diffusers release 🤗 Notes: https://github.com/huggingface/diffusers/releases/tag/v0.32.0

updated a Space 6 days ago

SmolTuners/README

View all activity

Organizations

s3nh's activity

reacted to sayakpaul's post with 🔥 5 days ago

Post

3626

Commits speak louder than words 🤪

* 4 new video models
* Multiple image models, including SANA & Flux Control
* New quantizers -> GGUF & TorchAO
* New training scripts

Enjoy this holiday-special Diffusers release 🤗
Notes: https://github.com/huggingface/diffusers/releases/tag/v0.32.0

reacted to merve's post with 🧠 11 days ago

Post

1717

A complete RAG pipeline includes a reranker, which ranks the documents to find the best document 📓
Same goes for multimodal RAG, multimodal rerankers which we can integrate to multimodal RAG pipelines!
Learn how to build a complete multimodal RAG pipeline with vidore/colqwen2-v1.0 as retriever, lightonai/MonoQwen2-VL-v0.1 as reranker, Qwen/Qwen2-VL-7B-Instruct as VLM in this notebook that runs on a GPU as small as L4 🔥 https://huggingface.co/learn/cookbook/multimodal_rag_using_document_retrieval_and_reranker_and_vlms

reacted to fdaudens's post with 🤗 11 days ago

Post

1181

🤝 Want to share your AI models while protecting your work? Licenses are key!

Fascinating to see that nearly 60% of models on the Hub use Apache & MIT licenses.

Explore the viz here: huggingface/open-source-ai-year-in-review-2024

reacted to Lewdiculous's post with ➕ 11 days ago

Post

2180

Hello fellow LLMers, just a quick notice that some of my activity will be moved into the AetherArchitectural Commuity and split with @Aetherarchio .

[here] https://huggingface.co/AetherArchitectural

All activity should be visible in the left side of my profile.

1 reply

reacted to fdaudens's post with 👍 11 days ago

Post

1204

🔍 From instruction-following to creative storytelling, dive into 2024's most impactful AI datasets! These gems are shaping everything from scientific research to video understanding.

Check it out: huggingface/open-source-ai-year-in-review-2024

replied to louisbrulenaudet's post 11 days ago

very useful, thanks!

reacted to louisbrulenaudet's post with 🤗 11 days ago

Post

1754

I’ve published a new dataset to simplify model merging 🤗

This dataset facilitates the search for compatible architectures for model merging with @arcee_ai’s mergekit, streamlining the automation of high-performance merge searches 📖

Dataset : louisbrulenaudet/mergekit-configs

1 reply

reacted to nyuuzyou's post with 👍 11 days ago

Post

1507

✈️ Aircraft Dataset & Generation Model nyuuzyou/aircraft-images & nyuuzyou/AircraftFLUX-LoRA

Dataset Features:
• 165,340 high-res aircraft images with metadata
• Machine-generated English captions
• Detailed aircraft specs, registration & flight info
• Environmental context descriptions

LoRA model specializes in:
• Realistic aircraft generation
• Accurate technical details for unpopular airplanes compared to black-forest-labs/FLUX.1-schnell
• Proper airline liveries
• Contextual aviation scenes

replied to danielhanchen's post 11 days ago

Amazing, thank you!

reacted to danielhanchen's post with 🤗👍 11 days ago

Post

1442

I uploaded GGUFs, 4bit bitsandbytes and full 16bit precision weights for Llama 3.3 70B Instruct are here: unsloth/llama-33-all-versions-67535d7d994794b9d7cf5e9f

You can also finetune Llama 3.3 70B in under 48GB of VRAM with Unsloth!
GGUFs: unsloth/Llama-3.3-70B-Instruct-GGUF
BnB 4bit: unsloth/Llama-3.3-70B-Instruct-bnb-4bit
16bit: unsloth/Llama-3.3-70B-Instruct

1 reply

reacted to stefan-it's post with ❤️ 11 days ago

Post

1159

My latest project is the outcome of the last 2+ years working with TPUs from the amazing TPU Research Cloud (TRC) program and training Encoder-only LMs with the TensorFlow Model Garden library.

👉 Link: https://github.com/stefan-it/model-garden-lms

An overview of some features:

- Cheatsheet for setting-up a TPU VM Pod (with all necessary dependencies) to pretrain LMs with TF Model Garden
- Conversion scripts that convert TF Model Garden weights to Hugging Face Transformers-compatible models
- Supported architectures include BERT, BERT with Token Dropping and TEAMS

I also released BERT-based models pretrained on the great Hugging Face FineWeb and FineWeb-Edu datasets (10BT subset). With more to come!

👉 Model Hub Link: https://huggingface.co/model-garden-lms

If you find these resources useful, please give them a like!

Made from Bavarian Oberland with ❤️ and 🥨.

reacted to lucifertrj's post with 👀 11 days ago

Post

490

Image Prompt Engineering Guide:
➡️ Artistic styling for Image generation
➡️ Prompt weighting using the parentheses method to generate realistic images.
➡️ Advanced features like style and positioning control[experimental].
➡️ Image placement on the generated AI image using Recraft V3 Mockup.

Watch: https://www.youtube.com/watch?v=d3nUG28-jIc

replied to AtAndDev's post 11 days ago

Sent u an email

reacted to davidberenstein1957's post with 🔥 11 days ago

Post

1307

🐇 Tumble down the AI rabbit hole without any technical knowledge!

Explore AI models on the Hub by a simple and quick search

Demo: davidberenstein1957/transformers-pipeline-playground

replied to davidberenstein1957's post 11 days ago

Looking great, cznnot wait to test, thank you 🤗

reacted to davidberenstein1957's post with ❤️🔥 11 days ago

Post

4138

Introducing the Synthetic Data Generator, a user-friendly application that takes a no-code approach to creating custom datasets with Large Language Models (LLMs). The best part: A simple step-by-step process, making dataset creation a non-technical breeze, allowing anyone to create datasets and models in minutes and without any code.

Blog: https://huggingface.co/blog/synthetic-data-generator
Space: argilla/synthetic-data-generator

4 replies

reacted to m-ric's post with 🚀 11 days ago

Post

2465

💥 𝗚𝗼𝗼𝗴𝗹𝗲 𝗿𝗲𝗹𝗲𝗮𝘀𝗲𝘀 𝗚𝗲𝗺𝗶𝗻𝗶 𝟮.𝟬, 𝘀𝘁𝗮𝗿𝘁𝗶𝗻𝗴 𝘄𝗶𝘁𝗵 𝗮 𝗙𝗹𝗮𝘀𝗵 𝗺𝗼𝗱𝗲𝗹 𝘁𝗵𝗮𝘁 𝘀𝘁𝗲𝗮𝗺𝗿𝗼𝗹𝗹𝘀 𝗚𝗣𝗧-𝟰𝗼 𝗮𝗻𝗱 𝗖𝗹𝗮𝘂𝗱𝗲-𝟯.𝟲 𝗦𝗼𝗻𝗻𝗲𝘁! And they start a huge effort on agentic capabilities.

🚀 The performance improvements are crazy for such a fast model:
‣ Gemini 2.0 Flash outperforms the previous 1.5 Pro model at twice the speed
‣ Now supports both input AND output of images, video, audio and text
‣ Can natively use tools like Google Search and execute code

➡️ If the price is on par with previous Flash iteration ($0.30 / M tokens, to compare with GPT-4o's $1.25) the competition will have a big problem with this 4x cheaper model that gets better benchmarks 🤯

🤖 What about the agentic capabilities?

‣ Project Astra: A universal AI assistant that can use Google Search, Lens and Maps
‣ Project Mariner: A Chrome extension that can complete complex web tasks (83.5% success rate on WebVoyager benchmark, this is really impressive!)
‣ Jules: An AI coding agent that integrates with GitHub workflows

I'll be eagerly awaiting further news from Google!

Read their blogpost here 👉 https://blog.google/technology/google-deepmind/google-gemini-ai-update-december-2024/

replied to MoritzLaurer's post 11 days ago

Looking great, thanks! Gonna try it ngl