s3nh's picture

s3nh

s3nh

AI & ML interests

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

Recent Activity

Organizations

ESPnet's profile picture Gradio-Blocks-Party's profile picture Lajonbot's profile picture The Waifu Research Department's profile picture AblateIt's profile picture Blog-explorers's profile picture BangumiBase's profile picture CyberHarem's profile picture HydraLM's profile picture GOAT.AI's profile picture That Time I got Reincarnated as a Hugging Face Organization's profile picture ZeroGPU Explorers's profile picture Social Post Explorers's profile picture Spinner-GPT-4's profile picture Hugging Face Discord Community's profile picture open/ acc's profile picture Smol Community's profile picture

s3nh's activity

reacted to YannisTevissen's post with ๐Ÿ‘๐Ÿค— 3 days ago
New activity in SmolTuners/README 3 days ago

Gh organization

8
#3 opened 25 days ago by
s3nh
reacted to sayakpaul's post with ๐Ÿ”ฅ 23 days ago
view post
Post
4065
Commits speak louder than words ๐Ÿคช

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

Enjoy this holiday-special Diffusers release ๐Ÿค—
Notes: https://github.com/huggingface/diffusers/releases/tag/v0.32.0
updated a Space 24 days ago
New activity in SmolTuners/README 25 days ago

Optimizers

#2 opened 25 days ago by
s3nh
New activity in SmolTuners/README 27 days ago

Datasets

3
#1 opened 29 days ago by
s3nh
reacted to merve's post with ๐Ÿง  29 days ago
view post
Post
1773
A complete RAG pipeline includes a reranker, which ranks the documents to find the best document ๐Ÿ““
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 ๐Ÿ”ฅ https://huggingface.co/learn/cookbook/multimodal_rag_using_document_retrieval_and_reranker_and_vlms
reacted to fdaudens's post with ๐Ÿค— 29 days ago
view post
Post
1289
๐Ÿค 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 โž• 29 days ago
view post
Post
3918
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
ยท
reacted to fdaudens's post with ๐Ÿ‘ 29 days ago
view post
Post
1350
๐Ÿ” 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 29 days ago
reacted to louisbrulenaudet's post with ๐Ÿค— 29 days ago
view post
Post
1834
Iโ€™ve published a new dataset to simplify model merging ๐Ÿค—

This dataset facilitates the search for compatible architectures for model merging with @arcee_aiโ€™s mergekit, streamlining the automation of high-performance merge searches ๐Ÿ“–

Dataset : louisbrulenaudet/mergekit-configs
  • 1 reply
ยท
reacted to nyuuzyou's post with ๐Ÿ‘ 29 days ago
view post
Post
1512
โœˆ๏ธ Aircraft Dataset & Generation Model nyuuzyou/aircraft-images & nyuuzyou/AircraftFLUX-LoRA

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

LoRA model specializes in:
โ€ข Realistic aircraft generation
โ€ข Accurate technical details for unpopular airplanes compared to black-forest-labs/FLUX.1-schnell
โ€ข Proper airline liveries
โ€ข Contextual aviation scenes
replied to danielhanchen's post 29 days ago