Hugging Face's logo

Hugging Face TB Research

Enterprise
community
Activity Feed

AI & ML interests

Exploring smol models and high quality web and synthetic datasets, generated by LLMs (TB is for Textbook, as inspired by the "Textbooks are all your need" paper)

Recent Activity

andito  new activity 1 day ago
HuggingFaceTB/SmolVLM-256M-Instruct:Upload photo_2025-01-25_13-45-22.jpg
andito  new activity 1 day ago
HuggingFaceTB/SmolVLM-256M-Instruct:E-MOBI / EKONOMIK MOBIL
andito  new activity 1 day ago
HuggingFaceTB/SmolVLM-256M-Instruct:There is an issue with AutoProcessor
View all activity

HuggingFaceTB's activity

fdaudens 
posted an update about 2 hours ago
view post
Post
81
📊 R1 just built its own download dashboard!

Some fresh stats: +6M downloads for 800+ derivative models vs 2M for originals. Watch the numbers grow here: fdaudens/deepseek-download-stats
andito 
in HuggingFaceTB/SmolVLM-256M-Instruct 1 day ago

Upload photo_2025-01-25_13-45-22.jpg
#5 opened 9 days ago by
Moeu

E-MOBI / EKONOMIK MOBIL
#7 opened 6 days ago by
jesus-christ666

There is an issue with AutoProcessor

2
#6 opened 8 days ago by
Tech-Meld
andito 
updated 2 models 1 day ago
merve 
posted an update 2 days ago
view post
Post
2670
This week in open AI was 🔥 Let's recap! 🤗 merve/january-31-releases-679a10669bd4030090c5de4d
LLMs 💬
> Huge: AllenAI released new Tülu models that outperform DeepSeek R1 using Reinforcement Learning with Verifiable Reward (RLVR) based on Llama 3.1 405B 🔥
> Mistral AI is back to open-source with their "small" 24B models (base & SFT), with Apache 2.0 license 😱
> Alibaba Qwen released their 1M context length models Qwen2.5-Instruct-1M, great for agentic use with Apache 2.0 license 🔥
> Arcee AI released Virtuoso-medium, 32.8B LLMs distilled from DeepSeek V3 with dataset of 5B+ tokens
> Velvet-14B is a new family of 14B Italian LLMs trained on 10T tokens in six languages
> OpenThinker-7B is fine-tuned version of Qwen2.5-7B-Instruct on OpenThoughts dataset

VLMs & vision 👀
> Alibaba Qwen is back with Qwen2.5VL, amazing new capabilities ranging from agentic computer use to zero-shot localization 🔥
> NVIDIA released new series of Eagle2 models with 1B and 9B sizes
> DeepSeek released Janus-Pro, new any-to-any model (image-text generation from image-text input) with MIT license
> BEN2 is a new background removal model with MIT license!

Audio 🗣️
> YuE is a new open-source music generation foundation model, lyrics-to-song generation

Codebase 👩🏻‍💻
> We are open-sourcing our SmolVLM training and eval codebase! https://github.com/huggingface/smollm/tree/main/vision
> Open-R1 is open-source reproduction of R1 by @huggingface science team https://huggingface.co./blog/open-r1
  • 1 reply
·
fdaudens 
posted an update 3 days ago
view post
Post
2904
🎯 Kokoro TTS just hit v1.0! 🚀

Small but mighty: 82M parameters, runs locally, speaks multiple languages. The best part? It's Apache 2.0 licensed!
This could unlock so many possibilities ✨

Check it out: hexgrad/Kokoro-82M
  • 1 reply
·
davidberenstein1957 
posted an update 4 days ago
loubnabnl 
updated a model 4 days ago
fdaudens 
posted an update 4 days ago
view post
Post
1169
💪 The open-source community is really unstoppable:

+5M total downloads for DeepSeek models on @hf .co
+4M are from the 700 models created by the community
That's 30% more than yesterday!
davanstrien 
posted an update 4 days ago
cfahlgren1 
posted an update 5 days ago
view post
Post
1748
If you haven't seen yet, we just released Inference Providers 🔀

> 4 new serverless inference providers on the Hub 🤯
> Use your HF API key or personal key with all providers 🔑
> Chat with Deepseek R1, V3, and more on HF Hub 🐋
> We support Sambanova, TogetherAI, Replicate, and Fal.ai 💪

Best of all, we don't charge any markup on top of the provider 🫰 Have you tried it out yet? HF Pro accounts get $2 of free usage for the provider inference.
fdaudens 
posted an update 5 days ago
view post
Post
1625
🚀 The open source community is unstoppable: 4M total downloads for DeepSeek models on Hugging Face, with 3.2M coming from the +600 models created by the community.

That's 30% more than yesterday!
  • 1 reply
·
davanstrien 
posted an update 6 days ago
fdaudens 
posted an update 6 days ago
view post
Post
7817
Yes, DeepSeek R1's release is impressive. But the real story is what happened in just 7 days after:

- Original release: 8 models, 540K downloads. Just the beginning...

- The community turned those open-weight models into +550 NEW models on Hugging Face. Total downloads? 2.5M—nearly 5X the originals.

The reason? DeepSeek models are open-weight, letting anyone build on top of them. Interesting to note that the community focused on quantized versions for better efficiency & accessibility. They want models that use less memory, run faster, and are more energy-efficient.

When you empower builders, innovation explodes. For everyone. 🚀

The most popular community model? @bartowski 's DeepSeek-R1-Distill-Qwen-32B-GGUF version — 1M downloads alone.
·
davanstrien 
posted an update 6 days ago
view post
Post
1933
🌍 Big step for multilingual AI data!

The Hugging Face community has rated educational content in languages spoken by 1.6 billion people! New additions:
• Japanese
• Italian
• Old High German

Learn more and contribute: https://huggingface.co./blog/davanstrien/fineweb2-community

These ratings can help enhance training data for major world languages.
  • 1 reply
·
davidberenstein1957 
posted an update 7 days ago
lewtun 
posted an update 8 days ago
view post
Post
9684
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
·
merve 
posted an update 9 days ago
view post
Post
4612
Oof, what a week! 🥵 So many things have happened, let's recap! merve/jan-24-releases-6793d610774073328eac67a9

Multimodal 💬
- We have released SmolVLM -- tiniest VLMs that come in 256M and 500M, with it's retrieval models ColSmol for multimodal RAG 💗
- UI-TARS are new models by ByteDance to unlock agentic GUI control 🤯 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 📖
- DeepSeek-R1 & DeepSeek-R1-Zero: gigantic 660B reasoning models by DeepSeek, and six distilled dense models, on par with o1 with MIT license! 🤯
- 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 🗣️
- 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 ⏯️
- 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
·