loubnabnl (Loubna Ben Allal)

reacted to lysandre's post with ❤️ 19 days ago

Post

5605

SmolVLM-2 and SigLIP-2 are now part of transformers in dedicated releases!

They're added on top of the v4.49.0 release, and can be installed from the following tags: v4.49.0-SmolVLM-2 and v4.49.0-SigLIP-2.

This marks a new beginning for the release process of transformers. For the past five years, we've been doing monthly releases featuring many models (v4.49.0, the latest release, features 9 new architectures).

Starting with SmolVLM-2 & SigLIP2, we'll now additionally release tags supporting new models on a stable branch. These models are therefore directly available for use by installing from the tag itself. These tags will continue to be updated with fixes applied to these models.

Going forward, continue expecting software releases following semantic versioning: v4.50.0 will have ~10 new architectures compared to v4.49.0, as well as a myriad of new features, improvements and bug fixes. Accompanying these software releases, we'll release tags offering brand new models as fast as possible, to make them accessible to all immediately.

1 reply

·

reacted to lewtun's post with 🔥 about 2 months ago

Post

10240

We are reproducing the full DeepSeek R1 data and training pipeline so everybody can use their recipe. Instead of doing it in secret we can do it together in the open!

🧪 Step 1: replicate the R1-Distill models by distilling a high-quality reasoning corpus from DeepSeek-R1.

🧠 Step 2: replicate the pure RL pipeline that DeepSeek used to create R1-Zero. This will involve curating new, large-scale datasets for math, reasoning, and code.

🔥 Step 3: show we can go from base model -> SFT -> RL via multi-stage training.

Follow along: https://github.com/huggingface/open-r1

5 replies

·

reacted to ginipick's post with 🔥 3 months ago

Post

4395

🌟 Digital Odyssey: AI Image & Video Generation Platform 🎨
Welcome to our all-in-one AI platform for image and video generation! 🚀
✨ Key Features

🎨 High-quality image generation from text
🎥 Video creation from still images
🌐 Multi-language support with automatic translation
🛠️ Advanced customization options

💫 Unique Advantages

⚡ Fast and accurate results using FLUX.1-dev and Hyper-SD models
🔒 Robust content safety filtering system
🎯 Intuitive user interface
🛠️ Extended toolkit including image upscaling and logo generation

🎮 How to Use

Enter your image or video description
Adjust settings as needed
Click generate
Save and share your results automatically

🔧 Tech Stack

FluxPipeline
Gradio
PyTorch
OpenCV

link: ginigen/Dokdo

Turn your imagination into reality with AI! ✨
#AI #ImageGeneration #VideoGeneration #MachineLearning #CreativeTech

7 replies

·

reacted to anton-l's post with 🚀🔥 3 months ago

Post

2576

Introducing 📐𝐅𝐢𝐧𝐞𝐌𝐚𝐭𝐡: the best public math pre-training dataset with 50B+ tokens!
HuggingFaceTB/finemath

Math remains challenging for LLMs and by training on FineMath we see considerable gains over other math datasets, especially on GSM8K and MATH.

We build the dataset by:
🛠️ carefully extracting math data from Common Crawl;
🔎 iteratively filtering and recalling high quality math pages using a classifier trained on synthetic annotations to identify math reasoning and deduction.

We conducted a series of ablations comparing the performance of Llama-3.2-3B-Base after continued pre-training on FineMath and observe notable gains compared to the baseline model and other public math datasets.

We hope this helps advance the performance of LLMs on math and reasoning! 🚀
We’re also releasing all the ablation models as well as the evaluation code.

HuggingFaceTB/finemath-6763fb8f71b6439b653482c2

reacted to julien-c's post with 🔥❤️🤗 3 months ago

Post

10348

After some heated discussion 🔥, we clarify our intent re. storage limits on the Hub

TL;DR:
- public storage is free, and (unless blatant abuse) unlimited. We do ask that you consider upgrading to PRO and/or Enterprise Hub if possible
- private storage is paid above a significant free tier (1TB if you have a paid account, 100GB otherwise)

docs: https://huggingface.co/docs/hub/storage-limits

We optimize our infrastructure continuously to scale our storage for the coming years of growth in Machine learning, to the benefit of the community 🔥

cc: @reach-vb @pierric @victor and the HF team

28 replies

·

reacted to clem's post with 🔥❤️ 3 months ago

Post

4435

HF中国镜像站 is becoming the best place to share the most viral AI apps with spaces.

Kolors Virtual Try-on just crossed 6,000,000 unique visitors & is now the #5 most popular space. Congrats to the Kwai Kolors team!

Kwai-Kolors/Kolors-Virtual-Try-On

2 replies

·

reacted to merve's post with 🔥 3 months ago

Post

2939

Last week we were blessed with open-source models! A recap 💝
merve/nov-29-releases-674ccc255a57baf97b1e2d31

🖼️ Multimodal
> At HF中国镜像站 we released SmolVLM, a performant and efficient smol vision language model 💗
> Show Lab released ShowUI-2B: new vision-language-action model to build GUI/web automation agents 🤖
> Rhymes AI has released the base model of Aria: Aria-Base-64K and Aria-Base-8K with their respective context length
> ViDoRe team released ColSmolVLM: A new ColPali-like retrieval model based on SmolVLM
> Dataset: Llava-CoT-o1-Instruct: new dataset labelled using Llava-CoT multimodal reasoning model📖
> Dataset: LLaVA-CoT-100k dataset used to train Llava-CoT released by creators of Llava-CoT 📕

💬 LLMs
> Qwen team released QwQ-32B-Preview, state-of-the-art open-source reasoning model, broke the internet 🔥
> AliBaba has released Marco-o1, a new open-source reasoning model 💥
> NVIDIA released Hymba 1.5B Base and Instruct, the new state-of-the-art SLMs with hybrid architecture (Mamba + transformer)

⏯️ Image/Video Generation
> Qwen2VL-Flux: new image generation model based on Qwen2VL image encoder, T5 and Flux for generation
> Lightricks released LTX-Video, a new DiT-based video generation model that can generate 24 FPS videos at 768x512 res ⏯️
> Dataset: Image Preferences is a new image generation preference dataset made with DIBT community effort of Argilla 🏷️

Audio
> OuteAI released OuteTTS-0.2-500M new multilingual text-to-speech model based on Qwen-2.5-0.5B trained on 5B audio prompt tokens

reacted to julien-c's post with 👀🔥 3 months ago

Post

3197

wow 😮

INTELLECT-1 is the first collaboratively trained 10 billion parameter language model trained from scratch on 1 trillion tokens of English text and code.

PrimeIntellect/INTELLECT-1-Instruct

reacted to merve's post with 🔥 4 months ago

Post

3954

Small yet mighty! 💫

We are releasing SmolVLM: a new 2B small vision language made for on-device use, fine-tunable on consumer GPU, immensely memory efficient 🤠

We release three checkpoints under Apache 2.0: SmolVLM-Instruct, SmolVLM-Synthetic and SmolVLM-Base HuggingFaceTB/smolvlm-6740bd584b2dcbf51ecb1f39

Learn more from our blog here: huggingface.co/blog/smolvlm
This release comes with a demo, fine-tuning code, MLX integration and TRL integration for DPO 💝
Try the demo: HuggingFaceTB/SmolVLM
Fine-tuning Recipe: https://github.com/huggingface/smollm/blob/main/finetuning/Smol_VLM_FT.ipynb
Also TRL integration for DPO 💗

reacted to thomwolf's post with 🔥 4 months ago

Post

1770

Interesting long read from @evanmiller-anthropic on having a better founded statistical approach to Language Model Evaluations:
https://www.anthropic.com/research/statistical-approach-to-model-evals

Worth a read if you're into LLM evaluations!

Cc @clefourrier

1 reply

·

reacted to openfree's post with 👀🔥 4 months ago

Post

3190

🤗 HuggingFace Trending TOP 300 Board - Featuring AI Rating System
📊 Service Introduction
A comprehensive dashboard that provides at-a-glance access to the real-time TOP 300 trending Spaces, Models, and Datasets on HuggingFace.
Our specially developed AI rating system evaluates the practical value and growth potential of each item.
⭐ Key Features
1. AI Rising Rate

Growth potential evaluation based on creation date and ranking
5-tier star rating system (★★★★★)
Evaluation Criteria:

Recency: Higher relative weights for recently created items
Ranking Impact: Higher relative weights for top rankings
Comprehensive assessment using statistical/analytical models applied to AI

2. AI Popularity Score

Comprehensive evaluation combining objective popularity and Rising Rate
18-tier grading system from AAA+ to B-
Evaluation Elements:

Base Score: Benchmark based on likes, downloads, comments, etc.
Additional Score: Rising Rate applied as a weighted factor
Comprehensive assessment using statistical/analytical models applied to AI

3. Visualization Features

Real-time screenshot capture with caching
Intuitive card-based UI
Responsive grid layout
Pastel gradient design

🎯 Applications

AI/ML Project Trend Analysis
Early Discovery of Promising Models/Datasets
Community Activity Monitoring
Research/Development Direction Reference

💡 Key Advantages

Real-time TOP 300 ranking
AI-based objective evaluation system
Fast loading with caching system
Intuitive and modern UI/UX
Integrated dashboard for 3 categories

🔄 Update Cycle

Real-time data reflection
Manual refresh option
Minimized server load through screenshot caching

🎁 Future Plans

Addition of detailed analysis report feature
Custom filtering options
Time-series trend analysis
Category-specific detailed statistics

🌐 How to Access
openfree/trending-board

#HuggingFace #AI #MachineLearning #TrendingBoard #DataScience #

3 replies

·

posted an update 4 months ago

Post

3046

Making SmolLM2 reproducible: open-sourcing our training & evaluation toolkit 🛠️ https://github.com/huggingface/smollm/

- Pre-training code with nanotron
- Evaluation suite with lighteval
- Synthetic data generation using distilabel (powers our new SFT dataset HuggingFaceTB/smoltalk)
- Post-training scripts with TRL & the alignment handbook
- On-device tools with llama.cpp for summarization, rewriting & agents

Apache 2.0 licensed. V2 pre-training data mix coming soon!

Which other tools should we add next?