Simon Pagezy's picture

Simon Pagezy

pagezyhf

AI & ML interests

Healthcare ML

Recent Activity

Articles

Organizations

Hugging Face's profile picture AWS Inferentia and Trainium's profile picture Hugging Face Optimum's profile picture Hugging Test Lab's profile picture Hugging Face OSS Metrics's profile picture Core ML Projects's profile picture Blog-explorers's profile picture Amazon SageMaker's profile picture Enterprise Explorers's profile picture Paris AI Running Club's profile picture Google Cloud ๐Ÿค๐Ÿป Hugging Face's profile picture PagezyTest's profile picture

pagezyhf's activity

reacted to m-ric's post with ๐Ÿš€ about 21 hours ago
view post
Post
2288
๐—ง๐—ต๐—ฒ ๐—›๐˜‚๐—ฏ ๐˜„๐—ฒ๐—น๐—ฐ๐—ผ๐—บ๐—ฒ๐˜€ ๐—ฒ๐˜…๐˜๐—ฒ๐—ฟ๐—ป๐—ฎ๐—น ๐—ถ๐—ป๐—ณ๐—ฒ๐—ฟ๐—ฒ๐—ป๐—ฐ๐—ฒ ๐—ฝ๐—ฟ๐—ผ๐˜ƒ๐—ถ๐—ฑ๐—ฒ๐—ฟ๐˜€!

โœ… Hosting our own inference was not enough: now the Hub 4 new inference providers: fal, Replicate, SambaNova Systems, & Together AI.

Check model cards on the Hub: you can now, in 1 click, use inference from various providers (cf video demo)

Their inference can also be used through our Inference API client. There, you can use either your custom provider key, or your HF token, then billing will be handled directly on your HF account, as a way to centralize all expenses.

๐Ÿ’ธ Also, PRO users get 2$ inference credits per month!

Read more in the announcement ๐Ÿ‘‰ https://huggingface.co/blog/inference-providers
  • 1 reply
ยท
reacted to merve's post with ๐Ÿ‘ 3 days ago
view post
Post
4322
Oof, what a week! ๐Ÿฅต So many things have happened, let's recap! merve/jan-24-releases-6793d610774073328eac67a9

Multimodal ๐Ÿ’ฌ
- We have released SmolVLM -- tiniest VLMs that come in 256M and 500M, with it's retrieval models ColSmol for multimodal RAG ๐Ÿ’—
- UI-TARS are new models by ByteDance to unlock agentic GUI control ๐Ÿคฏ in 2B, 7B and 72B
- Alibaba DAMO lab released VideoLlama3, new video LMs that come in 2B and 7B
- MiniMaxAI released Minimax-VL-01, where decoder is based on MiniMax-Text-01 456B MoE model with long context
- Dataset: Yale released a new benchmark called MMVU
- Dataset: CAIS released Humanity's Last Exam (HLE) a new challenging MM benchmark

LLMs ๐Ÿ“–
- DeepSeek-R1 & DeepSeek-R1-Zero: gigantic 660B reasoning models by DeepSeek, and six distilled dense models, on par with o1 with MIT license! ๐Ÿคฏ
- Qwen2.5-Math-PRM: new math models by Qwen in 7B and 72B
- NVIDIA released AceMath and AceInstruct, new family of models and their datasets (SFT and reward ones too!)

Audio ๐Ÿ—ฃ๏ธ
- Llasa is a new speech synthesis model based on Llama that comes in 1B,3B, and 8B
- TangoFlux is a new audio generation model trained from scratch and aligned with CRPO

Image/Video/3D Generation โฏ๏ธ
- Flex.1-alpha is a new 8B pre-trained diffusion model by ostris similar to Flux
- tencent released Hunyuan3D-2, new 3D asset generation from images
ยท
reacted to burtenshaw's post with ๐Ÿ”ฅ 11 days ago
view post
Post
39119
Weโ€™re launching a FREE and CERTIFIED course on Agents!

We're thrilled to announce the launch of the Hugging Face Agents course on Learn! This interactive, certified course will guide you through building and deploying your own AI agents.

Here's what you'll learn:

- Understanding Agents: We'll break down the fundamentals of AI agents, showing you how they use LLMs to perceive their environment (observations), reason about it (thoughts), and take actions. Think of a smart assistant that can book appointments, answer emails, or even write code based on your instructions.
- Building with Frameworks: You'll dive into popular agent frameworks like LangChain, LlamaIndex and smolagents. These tools provide the building blocks for creating complex agent behaviors.
- Real-World Applications: See how agents are used in practice, from automating SQL queries to generating code and summarizing complex documents.
- Certification: Earn a certification by completing the course modules, implementing a use case, and passing a benchmark assessment. This proves your skills in building and deploying AI agents.
Audience

This course is designed for anyone interested in the future of AI. Whether you're a developer, data scientist, or simply curious about AI, this course will equip you with the knowledge and skills to build your own intelligent agents.

Enroll today and start building the next generation of AI agent applications!

https://bit.ly/hf-learn-agents
ยท
reacted to mlabonne's post with ๐Ÿค— 11 days ago
view post
Post
3516
๐Ÿ†• LLM Course 2025 edition!

I updated the LLM Scientist roadmap and added a ton of new information and references. It covers training, datasets, evaluation, quantization, and new trends like test-time compute scaling.

The LLM Course has been incredibly popular (41.3k stars!) and I've been touched to receive many, many messages about how it helped people in their careers.

I know how difficult this stuff can be, so I'm super proud of the impact it had. I want to keep updating it in 2025, especially with the LLM Engineer roadmap.

Thanks everyone, hope you'll enjoy it!

๐Ÿ’ป LLM Course: https://huggingface.co/blog/mlabonne/llm-course
reacted to merve's post with โค๏ธ 13 days ago
view post
Post
2531
Everything that happened this week in open AI, a recap ๐Ÿค  merve/jan-17-releases-678a673a9de4a4675f215bf5

๐Ÿ‘€ Multimodal
- MiniCPM-o 2.6 is a new sota any-to-any model by OpenBMB
(vision, speech and text!)
- VideoChat-Flash-Qwen2.5-2B is new video multimodal models by OpenGVLab that come in sizes 2B & 7B in resolutions 224 & 448
- ByteDance released larger SA2VA that comes in 26B parameters
- Dataset: VRC-Bench is a new diverse benchmark for multimodal LLM reasoning performance

๐Ÿ’ฌ LLMs
- MiniMax-Text-01 is a new huge language model (456B passive 45.9B active params) by MiniMaxAI with context length of 4M tokens ๐Ÿคฏ
- Dataset: Sky-T1-data-17k is a diverse dataset used to train Sky-T1-32B
- kyutai released Helium-1-Preview-2B is a new small multilingual LM
- Wayfarer-12B is a new LLM able to write D&D ๐Ÿง™๐Ÿปโ€โ™‚๏ธ
- ReaderLM-v2 is a new HTML parsing model by Jina AI

- Dria released, Dria-Agent-a-3B, new agentic coding model (Pythonic function calling) based on Qwen2.5 Coder
- Unsloth released Phi-4, faster and memory efficient Llama 3.3

๐Ÿ–ผ๏ธ Vision
- MatchAnything is a new foundation model for matching
- FitDit is a high-fidelity VTON model based on DiT architecture

๐Ÿ—ฃ๏ธ Audio
- OuteTTS-0.3-1B is a new multilingual text-to-speech model with voice cloning and emotion control capabilities

๐Ÿ“– Retrieval
- lightblue released a new reranker based on Qwen2.5 LB-reranker-0.5B-v1.0 that can handle 95+ languages
- cde-small-v2 is a new sota small retrieval model by
@jxm
posted an update 17 days ago
replied to singhsidhukuldeep's post 28 days ago
reacted to singhsidhukuldeep's post with ๐Ÿคฏ 28 days ago
view post
Post
1626
Excited to share insights from Walmart's groundbreaking semantic search system that revolutionizes e-commerce product discovery!

The team at Walmart Global Technology(the team that I am a part of ๐Ÿ˜ฌ) has developed a hybrid retrieval system that combines traditional inverted index search with neural embedding-based search to tackle the challenging problem of tail queries in e-commerce.

Key Technical Highlights:

โ€ข The system uses a two-tower BERT architecture where one tower processes queries and another processes product information, generating dense vector representations for semantic matching.

โ€ข Product information is enriched by combining titles with key attributes like category, brand, color, and gender using special prefix tokens to help the model distinguish different attribute types.

โ€ข The neural model leverages DistilBERT with 6 layers and projects the 768-dimensional embeddings down to 256 dimensions using a linear layer, achieving optimal performance while reducing storage and computation costs.

โ€ข To improve model training, they implemented innovative negative sampling techniques combining product category matching and token overlap filtering to identify challenging negative examples.

Production Implementation Details:

โ€ข The system uses a managed ANN (Approximate Nearest Neighbor) service to enable fast retrieval, achieving 99% recall@20 with just 13ms latency.

โ€ข Query embeddings are cached with preset TTL (Time-To-Live) to reduce latency and costs in production.

โ€ข The model is exported to ONNX format and served in Java, with custom optimizations like fixed input shapes and GPU acceleration using NVIDIA T4 processors.

Results:
The system showed significant improvements in both offline metrics and live experiments, with:
- +2.84% improvement in NDCG@10 for human evaluation
- +0.54% lift in Add-to-Cart rates in live A/B testing

This is a fantastic example of how modern NLP techniques can be successfully deployed at scale to solve real-world e-
  • 1 reply
ยท
reacted to julien-c's post with ๐Ÿ”ฅโค๏ธ about 2 months ago
view post
Post
8933
After some heated discussion ๐Ÿ”ฅ, 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 ๐Ÿ”ฅ

cc: @reach-vb @pierric @victor and the HF team
ยท
reacted to merve's post with โค๏ธ about 2 months ago
view post
Post
5621
This week in open-source AI was insane ๐Ÿค  A small recap๐Ÿ•บ๐Ÿป merve/dec-6-releases-67545caebe9fc4776faac0a3

Multimodal ๐Ÿ–ผ๏ธ
> Google shipped a PaliGemma 2, new iteration of PaliGemma with more sizes: 3B, 10B and 28B, with pre-trained and captioning variants ๐Ÿ‘
> OpenGVLab released InternVL2, seven new vision LMs in different sizes, with sota checkpoint with MIT license โœจ
> Qwen team at Alibaba released the base models of Qwen2VL models with 2B, 7B and 72B ckpts

LLMs ๐Ÿ’ฌ
> Meta released a new iteration of Llama 70B, Llama3.2-70B trained further
> EuroLLM-9B-Instruct is a new multilingual LLM for European languages with Apache 2.0 license ๐Ÿ”ฅ
> Dataset: CohereForAI released GlobalMMLU, multilingual version of MMLU with 42 languages with Apache 2.0 license
> Dataset: QwQ-LongCoT-130K is a new dataset to train reasoning models
> Dataset: FineWeb2 just landed with multilinguality update! ๐Ÿ”ฅ nearly 8TB pretraining data in many languages!

Image/Video Generation ๐Ÿ–ผ๏ธ
> Tencent released HunyuanVideo, a new photorealistic video generation model
> OminiControl is a new editing/control framework for image generation models like Flux

Audio ๐Ÿ”Š
> Indic-Parler-TTS is a new text2speech model made by community
posted an update about 2 months ago
reacted to fdaudens's post with โค๏ธ about 2 months ago
view post
Post
1774
Keeping up with open-source AI in 2024 = overwhelming.

Here's help: We're launching our Year in Review on what actually matters, starting today!

Fresh content dropping daily until year end. Come along for the ride - first piece out now with @clem 's predictions for 2025.

Think of it as your end-of-year AI chocolate calendar.

Kudos to @BrigitteTousi @clefourrier @Wauplin @thomwolf for making it happen. We teamed up with aiworld.eu for awesome visualizations to make this digestibleโ€”it's a charm to work with their team.

Check it out: huggingface/open-source-ai-year-in-review-2024
posted an update about 2 months ago
view post
Post
974
Itโ€™s 2nd of December , hereโ€™s your Cyber Monday present ๐ŸŽ !

Weโ€™re cutting our price down on Hugging Face Inference Endpoints and Spaces!

Our folks at Google Cloud are treating us with a 40% price cut on GCP Nvidia A100 GPUs for the next 3๏ธโƒฃ months. We have other reductions on all instances ranging from 20 to 50%.

Sounds like the time to give Inference Endpoints a try? Get started today and find in our documentation the full pricing details.
https://ui.endpoints.huggingface.co/
https://huggingface.co/pricing
reacted to Xenova's post with ๐Ÿš€ 2 months ago
view post
Post
4039
We just released Transformers.js v3.1 and you're not going to believe what's now possible in the browser w/ WebGPU! ๐Ÿคฏ Let's take a look:
๐Ÿ”€ Janus from Deepseek for unified multimodal understanding and generation (Text-to-Image and Image-Text-to-Text)
๐Ÿ‘๏ธ Qwen2-VL from Qwen for dynamic-resolution image understanding
๐Ÿ”ข JinaCLIP from Jina AI for general-purpose multilingual multimodal embeddings
๐ŸŒ‹ LLaVA-OneVision from ByteDance for Image-Text-to-Text generation
๐Ÿคธโ€โ™€๏ธ ViTPose for pose estimation
๐Ÿ“„ MGP-STR for optical character recognition (OCR)
๐Ÿ“ˆ PatchTST & PatchTSMixer for time series forecasting

That's right, everything running 100% locally in your browser (no data sent to a server)! ๐Ÿ”ฅ Huge for privacy!

Check out the release notes for more information. ๐Ÿ‘‡
https://github.com/huggingface/transformers.js/releases/tag/3.1.0

Demo link (+ source code): webml-community/Janus-1.3B-WebGPU
reacted to AdinaY's post with ๐Ÿ”ฅ 2 months ago
view post
Post
1629
๐ŸŒŠ The wave of reasoning models from the Chinese community has arrived!

๐Ÿš€ Marco-o1 by AIDC, Alibaba
๐Ÿ‘‰ AIDC-AI/Marco-o1

โœจ QwQ by Qwen, Alibaba
๐Ÿ‘‰ Qwen/qwq-674762b79b75eac01735070a

๐ŸŒŸ Skywork-o1 by Kunlun Tech
๐Ÿ‘‰ Skywork/skywork-o1-open-67453df58e12f6c3934738d0

๐Ÿ”ฅ Xkev/Llama-3.2V-11B-cot by PKU Yuan group
๐Ÿ‘‰ Xkev/Llama-3.2V-11B-cot

๐Ÿ’ก DeepSeek-R1-Lite-Preview by DeepSeek AI
๐Ÿ‘‰ https://chat.deepseek.com/

๐Ÿ” InternThinker Preview by Shanghai AI Lab
๐Ÿ‘‰ https://sso.openxlab.org.cn/login?redirect=https://internlm-chat.intern-ai.org.cn/&clientId=ebmrvod6yo0nlzaek1yp

๐Ÿ“˜ k0-math by Moonshot AI
๐Ÿš€ https://kimi.moonshot.cn/ ( coming soon! )

Who's next? ๐Ÿ‘€
zh-ai-community/reasoning-models-67409fb3aa1ed78f10087cd7
posted an update 2 months ago
view post
Post
304
Hello Hugging Face Community,

if you use Google Kubernetes Engine to host you ML workloads, I think this series of videos is a great way to kickstart your journey of deploying LLMs, in less than 10 minutes! Thank you @wietse-venema-demo !

To watch in this order:
1. Learn what are Hugging Face Deep Learning Containers
https://youtu.be/aWMp_hUUa0c?si=t-LPRkRNfD3DDNfr

2. Learn how to deploy a LLM with our Deep Learning Container using Text Generation Inference
https://youtu.be/Q3oyTOU1TMc?si=V6Dv-U1jt1SR97fj

3. Learn how to scale your inference endpoint based on traffic
https://youtu.be/QjLZ5eteDds?si=nDIAirh1r6h2dQMD

If you want more of these small tutorials and have any theme in mind, let me know!
posted an update 3 months ago
view post
Post
1363
Hello Hugging Face Community,

I'd like to share here a bit more about our Deep Learning Containers (DLCs) we built with Google Cloud, to transform the way you build AI with open models on this platform!

With pre-configured, optimized environments for PyTorch Training (GPU) and Inference (CPU/GPU), Text Generation Inference (GPU), and Text Embeddings Inference (CPU/GPU), the Hugging Face DLCs offer:

โšก Optimized performance on Google Cloud's infrastructure, with TGI, TEI, and PyTorch acceleration.
๐Ÿ› ๏ธ Hassle-free environment setup, no more dependency issues.
๐Ÿ”„ Seamless updates to the latest stable versions.
๐Ÿ’ผ Streamlined workflow, reducing dev and maintenance overheads.
๐Ÿ”’ Robust security features of Google Cloud.
โ˜๏ธ Fine-tuned for optimal performance, integrated with GKE and Vertex AI.
๐Ÿ“ฆ Community examples for easy experimentation and implementation.
๐Ÿ”œ TPU support for PyTorch Training/Inference and Text Generation Inference is coming soon!

Find the documentation at https://huggingface.co/docs/google-cloud/en/index
If you need support, open a conversation on the forum: https://discuss.huggingface.co/c/google-cloud/69
reacted to fdaudens's post with ๐Ÿ”ฅ 4 months ago
view post
Post
2105
IBM & NASA just released open-source AI model for weather & climate on Hugging Face.

Prithvi WxC offers insights beyond forecasting, tackling challenges from local weather to global climate. Potential apps: targeted forecasts, severe weather detection & more. https://huggingface.co/Prithvi-WxC

This is impressive. Check out this comparison of the Ida hurricane between ground truth and the AI model's prediction.
reacted to alvarobartt's post with ๐Ÿ”ฅ 4 months ago
view post
Post
2944
๐Ÿค— Serving Meta Llama 3.1 405B on Google Cloud is now possible via the Hugging Face Deep Learning Containers (DLCs) for Text Generation Inference (TGI)

In this post, we showcase how to deploy https://huggingface.co/meta-llama/Meta-Llama-3.1-405B-Instruct-FP8 on an A3 instance with 8 x H100 GPUs on Vertex AI

Thanks to the Hugging Face DLCs for TGI and Google Cloud Vertex AI, deploying a high-performance text generation container for serving Large Language Models (LLMs) has never been easier. And weโ€™re not going to stop here โ€“ stay tuned as we enable more experiences to build AI with open models on Google Cloud!

Read the full post at https://huggingface.co/blog/llama31-on-vertex-ai