clem (Clem 🤗)

reacted to Tonic's post with ❤️👍 5 days ago

Post

2998

🙋🏻‍♂️hey there folks,

periodic reminder : if you are experiencing ⚠️500 errors ⚠️ or ⚠️ abnormal spaces behavior on load or launch ⚠️

we have a thread 👉🏻 https://discord.com/channels/879548962464493619/1295847667515129877

if you can record the problem and share it there , or on the forums in your own post , please dont be shy because i'm not sure but i do think it helps 🤗🤗🤗

2 replies

·

reacted to vikhyatk's post with 🚀🔥 5 days ago

Post

3976

Pushed a new update to vikhyatk/moondream2 today. TextVQA up from 60.2 to 65.2, DocVQA up from 61.9 to 70.5.

Space has been updated to the new model if you want to try it out! vikhyatk/moondream2

reacted to merve's post with 👍❤️🔥 5 days ago

Post

4777

Another great week in open ML!
Here's a small recap 🫰🏻

Model releases
⏯️ Video Language Models
AI at Meta released Vision-CAIR/LongVU_Qwen2_7B, a new state-of-the-art long video LM model based on DINOv2, SigLIP, Qwen2 and Llama 3.2

💬 Small language models
Hugging Face released HuggingFaceTB/SmolLM2-1.7B, a family of new smol language models with Apache 2.0 license that come in sizes 135M, 360M and 1.7B, along with datasets.
Meta released facebook/MobileLLM-1B, a new family of on-device LLMs of sizes 125M, 350M and 600M

🖼️ Image Generation
Stability AI released stabilityai/stable-diffusion-3.5-medium, a 2B model with commercially permissive license

🖼️💬Any-to-Any
gpt-omni/mini-omni2 is closest reproduction to GPT-4o, a new LLM that can take image-text-audio input and output speech is released!

Dataset releases
🖼️ Spawning/PD12M, a new captioning dataset of 12.4 million examples generated using Florence-2

reacted to davidberenstein1957's post with ❤️ 5 days ago

Post

1662

You can now build a custom text classifier without days of human labeling!

👍 LLMs work reasonably well as text classifiers.
👎 They are expensive to run at scale and their performance drops in specialized domains.

👍 Purpose-built classifiers have low latency and can potentially run on CPU.
👎 They require labeled training data.

Combine the best of both worlds: the automatic labeling capabilities of LLMs and the high-quality annotations from human experts to train and deploy a specialized model.

Blog: https://huggingface.co/blog/sdiazlor/custom-text-classifier-ai-human-feedback

reacted to davidberenstein1957's post with 👀 5 days ago

Post

662

The Synthetic Data Generator now directly integrates with Argilla, so you can generate and curate your own high-quality datasets from pure natural language!

Up next -> include dataset generation for text classification.
Other suggestions? Let us know.

Space: argilla/synthetic-data-generator

reacted to MonsterMMORPG's post with ❤️👀🤯 5 days ago

Post

2294

OmniGen 1-Click Automatic Installers for Windows, RunPod and Massed Compute

OmniGen is a unified image generation model that can generate a wide range of images from multi-modal prompts. It is designed to be simple, flexible, and easy to use

Installers are here : https://www.patreon.com/posts/omnigen-1-click-115233922

Look attached images to understand what capabilities it has. It is simply amazing so many features.

What is OmniGen : https://github.com/VectorSpaceLab/OmniGen

Windows Requirements
Python 3.10.11, CUDA 12.4, Git, FFMPEG, cuDNN 9.x, C++ Tools

A tutorial that shows how to install all above : https://youtu.be/DrhUHnYfwC0

How To Install & Use
After installing requirements by following above tutorial, double-click Windows_Install.bat and install
After that use Windows_Start.bat to start the app

When offload_model is enabled (checked) on the Gradio interface, it uses 5.4 GB VRAM, 2x slower

When offload_model is not used (not checked) it uses 12.2 GB VRAM

When separate_cfg_infer is not checked, and offload_model is not checked, it uses 18.7 GB VRAM

To install on RunPod and Massed Compute please follow Massed_Compute_Instructions_READ.txt and Runpod_Instructions_READ.txt

Look at the examples on the Gradio interface closely to understand how to use

reacted to nbroad's post with 🤗 9 days ago

Post

3431

hi florent and livestream!

5 replies

·

reacted to singhsidhukuldeep's post with ❤️ 16 days ago

Post

2633

If you have ~300+ GB of V-RAM, you can run Mochi from @genmo

A SOTA model that dramatically closes the gap between closed and open video generation models.

Mochi 1 introduces revolutionary architecture featuring joint reasoning over 44,520 video tokens with full 3D attention. The model implements extended learnable rotary positional embeddings (RoPE) in three dimensions, with network-learned mixing frequencies for space and time axes.

The model incorporates cutting-edge improvements, including:
- SwiGLU feedforward layers
- Query-key normalization for enhanced stability
- Sandwich normalization for controlled internal activations

What is currently available?
The base model delivers impressive 480p video generation with exceptional motion quality and prompt adherence. Released under the Apache 2.0 license, it's freely available for both personal and commercial applications.

What's Coming?
Genmo has announced Mochi 1 HD, scheduled for release later this year, which will feature:
- Enhanced 720p resolution
- Improved motion fidelity
- Better handling of complex scene warping

2 replies

·

reacted to fdaudens's post with ❤️ 16 days ago

Post

2736

🤯 Plot twist: Size isn't everything in AI! A lean 32B parameter model just showed up to the party and outperformed a 70B one. Efficiency > Scale? The AI world just got more interesting...

Cohere For AI released Aya Expanse, a new family of multilingual models (8B and 32B) spanning 23 popular languages.

Models: CohereForAI/c4ai-aya-expanse-671a83d6b2c07c692beab3c3
Blog post: https://huggingface.co/blog/aya-expanse
Demo: CohereForAI/aya_expanse

posted an update 16 days ago

Post

4016

This is no Woodstock AI but will be fun nonetheless haha. I’ll be hosting a live workshop with team members next week about the Enterprise Hugging Face hub.

1,000 spots available first-come first serve with some surprises during the stream!

You can register and add to your calendar here: https://streamyard.com/watch/JS2jHsUP3NDM

4 replies

·

replied to malhajar's post 18 days ago

bravo!

reacted to malhajar's post with ❤️🔥 18 days ago

Post

3557

🇫🇷 Lancement officiel de l'OpenLLM French Leaderboard : initiative open-source pour référencer l’évaluation des LLMs francophones

Après beaucoup d’efforts et de sueurs avec Alexandre Lavallee, nous sommes ravis d’annoncer que le OpenLLMFrenchLeaderboard est en ligne sur Hugging Face (space url: le-leadboard/OpenLLMFrenchLeaderboard) la toute première plateforme dédiée à l’évaluation des grands modèles de langage (LLM) en français. 🇫🇷✨

Ce projet de longue haleine est avant tout une œuvre de passion mais surtout une nécessité absolue. Il devient urgent et vital d'oeuvrer à plus de transparence dans ce domaine stratégique des LLM dits multilingues. La première pièce à l'édifice est donc la mise en place d'une évaluation systématique et systémique des modèles actuels et futurs.

Votre modèle IA français est-il prêt à se démarquer ? Soumettez le dans notre espace, et voyez comment vous vous comparez par rapport aux autres modèles.

❓ Comment ça marche :
Soumettez votre LLM français pour évaluation, et nous le testerons sur des benchmarks de référence spécifiquement adaptés pour la langue française — notre suite de benchmarks comprend :

- BBH-fr : Raisonnement complexe
- IFEval-fr : Suivi d'instructions
- GPQA-fr : Connaissances avancées
- MUSR-fr : Raisonnement narratif
- MATH_LVL5-fr : Capacités mathématiques
- MMMLU-fr : Compréhension multitâche

Le processus est encore manuel, mais nous travaillons sur son automatisation, avec le soutien de la communauté Hugging Face.

@clem , on se prépare pour une mise à niveau de l’espace ? 😏👀

Ce n'est pas qu'une question de chiffres—il s'agit de créer une IA qui reflète vraiment notre langue, notre culture et nos valeurs. OpenLLMFrenchLeaderboard est notre contribution personnelle pour façonner l'avenir des LLM en France.

1 reply

·

reacted to reach-vb's post with 🚀 22 days ago

Post

2369

What a great day for Open Science! @AIatMeta released models, datasets, and code for many of its research artefacts! 🔥

1. Meta Segment Anything Model 2.1: An updated checkpoint with improved results on visually similar objects, small objects and occlusion handling. A new developer suite will be added to make it easier for developers to build with SAM 2.

Model checkpoints: reach-vb/sam-21-6702d40defe7611a8bafa881

2. Layer Skip: Inference code and fine-tuned checkpoints demonstrating a new method for enhancing LLM performance.

Model checkpoints: facebook/layerskip-666b25c50c8ae90e1965727a

3. SALSA: New code enables researchers to benchmark AI-based attacks to validate security for post-quantum cryptography.

Repo: https://github.com/facebookresearch/LWE-benchmarking

4. Meta Lingua: A lightweight and self-contained codebase designed to train language models at scale.

Repo: https://github.com/facebookresearch/lingua

5. Meta Open Materials: New open source models and the largest dataset to accelerate AI-driven discovery of new inorganic materials.

Model checkpoints: fairchem/OMAT24

6. MEXMA: A new research paper and code for our novel pre-trained cross-lingual sentence encoder covering 80 languages.

Model checkpoint: facebook/MEXMA

7. Self-Taught Evaluator: a new method for generating synthetic preference data to train reward models without relying on human annotations.

Model checkpoint: facebook/Self-taught-evaluator-llama3.1-70B

8. Meta Spirit LM: An open-source language model for seamless speech and text integration.

Repo: https://github.com/facebookresearch/spiritlm

3 replies

·

Clem 🤗 PRO

AI & ML interests

Organizations

clem's activity