111 13 229

s3nh

AI & ML interests

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

Recent Activity

liked a model 9 days ago

ByteDance-Seed/BAGEL-7B-MoT

liked a model 11 days ago

uwg/upscaler

reacted to KnutJaegersberg's post with ❤️ 16 days ago

The Intelligence Curse The document warns of the "intelligence curse," a potential consequence of advanced AI (AGI) where powerful entities lose their incentive to invest in people as AI automates work[cite: 13, 297]. This could lead to job displacement, reduced social mobility, and a concentration of power and wealth based on AI ownership, similar to the "resource curse" in resource-rich states[cite: 17, 18, 31, 329, 353]. To counter this, the authors propose averting AI catastrophes to prevent centralization, diffusing AI widely to keep humans economically relevant, and democratizing institutions to remain anchored to human needs[cite: 22, 23, 25, 35, 36, 37, 566]. https://intelligence-curse.ai/intelligence-curse.pdf

View all activity

Organizations

s3nh's activity

reacted to KnutJaegersberg's post with ❤️ 16 days ago

Post

2727

The Intelligence Curse

The document warns of the "intelligence curse," a potential consequence of advanced AI (AGI) where powerful entities lose their incentive to invest in people as AI automates work[cite: 13, 297]. This could lead to job displacement, reduced social mobility, and a concentration of power and wealth based on AI ownership, similar to the "resource curse" in resource-rich states[cite: 17, 18, 31, 329, 353]. To counter this, the authors propose averting AI catastrophes to prevent centralization, diffusing AI widely to keep humans economically relevant, and democratizing institutions to remain anchored to human needs[cite: 22, 23, 25, 35, 36, 37, 566].

https://intelligence-curse.ai/intelligence-curse.pdf

reacted to loubnabnl's post with ❤️ 16 days ago

Post

2629

SmolVLM is now available on PocketPal — you can run it offline on your smartphone to interpret the world around you. 🌍📱

And check out this real-time camera demo by @ngxson , powered by llama.cpp:
https://github.com/ngxson/smolvlm-realtime-webcam
https://x.com/pocketpal_ai

3 replies

reacted to merve's post with 👍🚀 16 days ago

Post

6572

A real-time object detector much faster and accurate than YOLO with Apache 2.0 license just landed to Hugging Face transformers 🔥

D-FINE is the sota real-time object detector that runs on T4 (free Colab) 🤩

> Collection with all checkpoints and demo ustc-community/d-fine-68109b427cbe6ee36b4e7352

Notebooks:
> Tracking https://github.com/qubvel/transformers-notebooks/blob/main/notebooks/DFine_tracking.ipynb
> Inference https://github.com/qubvel/transformers-notebooks/blob/main/notebooks/DFine_inference.ipynb
> Fine-tuning https://github.com/qubvel/transformers-notebooks/blob/main/notebooks/DFine_finetune_on_a_custom_dataset.ipynb
h/t @vladislavbro @qubvel-hf @ariG23498 and the authors of the paper 🎩

Regular object detectors attempt to predict bounding boxes in (x, y, w, h) pixel perfect coordinates, which is very rigid and hard to solve 🥲☹️

D-FINE formulates object detection as a distribution for bounding box coordinates, refines them iteratively, and it's more accurate 🤩

Another core idea behind this model is Global Optimal Localization Self-Distillation ⤵️

this model uses final layer's distribution output (sort of like a teacher) to distill to earlier layers to make early layers more performant.

2 replies

reacted to mrfakename's post with 👍🤗 17 days ago

Post

3211

Hi everyone,

I just launched TTS Arena V2 - a platform for benchmarking TTS models by blind A/B testing. The goal is to make it easy to compare quality between open-source and commercial models, including conversational ones.

What's new in V2:

- **Conversational Arena**: Evaluate models like CSM-1B, Dia 1.6B, and PlayDialog in multi-turn settings
- **Personal Leaderboard**: Optional login to see which models you tend to prefer
- **Multi-speaker TTS**: Random voices per generation to reduce speaker bias
- **Performance Upgrade**: Rebuilt from Gradio → Flask. Much faster with fewer failed generations.
- **Keyboard Shortcuts**: Vote entirely via keyboard

Also added models like MegaTTS 3, Cartesia Sonic, and ElevenLabs' full lineup.

I'd love any feedback, feature suggestions, or ideas for models to include.

TTS-AGI/TTS-Arena-V2

4 replies

reacted to merve's post with 🚀👍 about 1 month ago

Post

2211

you can easily fine-tune, quantize, play with sota vision LM InternVL3 now 🔥
we have recently merged InternVL3 to Hugging Face transformers and released converted checkpoints 🤗

collection for converted checkpoints: merve/internvl3-hf-6814be2943b2ae0e711c92a5
notebook: https://colab.research.google.com/drive/1wAQ7cyjyaCwLXbMA_OjXZe7aCxCFm6sI?usp=sharing 📖

reacted to merterbak's post with 🔥 about 1 month ago

Post

1694

Microsoft released their new fine-tuned phi-4 models with reasoning data yesterday. They outperform/rival much larger models . Check out them if you haven't yet. 🚀

Phi4 mini reasoning(SFT): microsoft/Phi-4-mini-reasoning
Phi-4 reasoning(SFT): microsoft/Phi-4-reasoning
Phi-4 reasoning plus (SFT + RL): microsoft/Phi-4-reasoning-plus
Demo: https://github.com/marketplace/models/azureml/Phi-4-reasoning/playground
Articles: https://arxiv.org/pdf/2504.21318
https://arxiv.org/pdf/2504.21233
Blog: https://azure.microsoft.com/en-us/blog/one-year-of-phi-small-language-models-making-big-leaps-in-ai/

1 reply

reacted to as-cle-bert's post with ❤️👍 3 months ago

Post

2751

I just released a fully automated evaluation framework for your RAG applications!📈

GitHub 👉 https://github.com/AstraBert/diRAGnosis
PyPi 👉 https://pypi.org/project/diragnosis/

It's called 𝐝𝐢𝐑𝐀𝐆𝐧𝐨𝐬𝐢𝐬 and is a lightweight framework that helps you 𝗱𝗶𝗮𝗴𝗻𝗼𝘀𝗲 𝘁𝗵𝗲 𝗽𝗲𝗿𝗳𝗼𝗿𝗺𝗮𝗻𝗰𝗲 𝗼𝗳 𝗟𝗟𝗠𝘀 𝗮𝗻𝗱 𝗿𝗲𝘁𝗿𝗶𝗲𝘃𝗮𝗹 𝗺𝗼𝗱𝗲𝗹𝘀 𝗶𝗻 𝗥𝗔𝗚 𝗮𝗽𝗽𝗹𝗶𝗰𝗮𝘁𝗶𝗼𝗻𝘀.

You can launch it as an application locally (it's Docker-ready!🐋) or, if you want more flexibility, you can integrate it in your code as a python package📦

The workflow is simple:
🧠 You choose your favorite LLM provider and model (supported, for now, are Mistral AI, Groq, Anthropic, OpenAI and Cohere)
🧠 You pick the embedding models provider and the embedding model you prefer (supported, for now, are Mistral AI, Hugging Face, Cohere and OpenAI)
📄 You prepare and provide your documents
⚙️ Documents are ingested into a Qdrant vector database and transformed into a synthetic question dataset with the help of LlamaIndex
📊 The LLM is evaluated for the faithfulness and relevancy of its retrieval-augmented answer to the questions
📊 The embedding model is evaluated for hit rate and mean reciprocal ranking (MRR) of the retrieved documents

And the cool thing is that all of this is 𝗶𝗻𝘁𝘂𝗶𝘁𝗶𝘃𝗲 𝗮𝗻𝗱 𝗰𝗼𝗺𝗽𝗹𝗲𝘁𝗲𝗹𝘆 𝗮𝘂𝘁𝗼𝗺𝗮𝘁𝗲𝗱: you plug it in, and it works!🔌⚡

Even cooler? This is all built on top of LlamaIndex and its integrations: no need for tons of dependencies or fancy workarounds🦙
And if you're a UI lover, Gradio and FastAPI are there to provide you a seamless backend-to-frontend experience🕶️

So now it's your turn: you can either get diRAGnosis from GitHub 👉 https://github.com/AstraBert/diRAGnosis
or just run a quick and painless:

uv pip install diragnosis

To get the package installed (lightning-fast) in your environment🏃‍♀️

Have fun and feel free to leave feedback and feature/integrations requests on GitHub issues✨

reacted to MonsterMMORPG's post with 🔥 3 months ago

Post

2424

Wan 2.1 Ultra Advanced Gradio APP for - Works as low as 4GB VRAM - 1-Click Installers for Windows, RunPod, Massed Compute - Batch Processing - T2V - I2V - V2V

Installer and APP : https://www.patreon.com/posts/123105403

Download from here : https://www.patreon.com/posts/123105403

I have been working 14 hours today to make this APP before sleeping for you guys :)

We have all the features of Wan 2.1 model

Text to Video 1.3B (as low as 3.5 GB VRAM) - Really fast - 480x832px or 832x480px

Video to Video 1.3B (as low as 3.5 GB VRAM) - Really fast - 480x832px or 832x480px

Text to Video 14B (as low as 17 GB VRAM) - still may work at below VRAM but slower - 720x1280px or 1280x720px

Image to Video 14B (as low as 17 GB VRAM) - still may work at below VRAM but slower - 720x1280px or 1280x720px

When you analyze the above and below images
First video is animated from the input image with following prompt

A hooded wraith stands motionless in a torrential downpour, lightning cracking across the stormy sky behind it. Its face is an impenetrable void of darkness beneath the tattered hood. Rain cascades down its ragged, flowing cloak, which appears to disintegrate into wisps of shadow at the edges. The mysterious figure holds an enormous sword of pure energy, crackling with electric blue lightning that pulses and flows through the blade like liquid electricity. The weapon drags slightly on the wet ground, sending ripples of power across the puddles forming at the figure's feet. Three glowing blue gems embedded in its chest pulse in rhythm with the storm's lightning strikes, each flash illuminating the decaying, ancient fabric of its attire. The rain intensifies around the figure, droplets seemingly slowing as they near the dark entity, while forks of lightning repeatedly illuminate its imposing silhouette. The atmosphere grows heavier with each passing moment as the wraith slowly raises its crackling blade, the blue energy intensifying and casting eerie shadows

3 replies

reacted to their post with 🤗 4 months ago

Post

2150

Welcome back,

Small Language Models Enthusiasts and GPU Poor oss enjoyers lets connect.
Just created an organization which main target is to have fun with smaller models tuneable on consumer range GPUs, feel free to join and lets have some fun, much love ;3

SmolTuners

3 replies

reacted to YannisTevissen's post with 👍🤗 5 months ago

Post

2283

Starting this collection to gather models, spaces, dataset or even papers related to disability. Feel free to ping me if you see something relevant to add

YannisTevissen/ai-for-disability-67684a1a9966a2e699f6b114

reacted to sayakpaul's post with 🔥 5 months ago

Post

4452

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 🧠 6 months ago

Post

1828

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

1 reply

reacted to fdaudens's post with 🤗 6 months ago

Post

1339

🤝 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 ➕ 6 months ago

Post

13780

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

[here]

AetherArchitectural

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

2 replies

reacted to fdaudens's post with 👍 6 months ago

Post

1404

🔍 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