Hugging Face's logo

Keras Dreambooth Event

community
Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

shivi  authored a paper 16 days ago
Aya Expanse: Combining Research Breakthroughs for a New Multilingual Frontier
shivi  authored a paper 19 days ago
INCLUDE: Evaluating Multilingual Language Understanding with Regional Knowledge
shivi  authored a paper 19 days ago
Global MMLU: Understanding and Addressing Cultural and Linguistic Biases in Multilingual Evaluation
View all activity

keras-dreambooth's activity

merve 
posted an update 1 day ago
sayakpaul 
posted an update 1 day ago
merve 
posted an update 7 days ago
view post
Post
2330
Aya by Cohere For AI can now see! 👀

C4AI community has built Maya 8B, a new open-source multilingual VLM built on SigLIP and Aya 8B 🌱 works on 8 languages! 🗣️

The authors extend Llava dataset using Aya's translation capabilities with 558k examples!
ry it here kkr5155/maya_demo

Dataset maya-multimodal/pretrain

Model maya-multimodal/maya 👏
kudos @nahidalam and team
  • 1 reply
·
sayakpaul 
posted an update 8 days ago
view post
Post
1552
In the past seven days, the Diffusers team has shipped:

1. Two new video models
2. One new image model
3. Two new quantization backends
4. Three new fine-tuning scripts
5. Multiple fixes and library QoL improvements

Coffee on me if someone can guess 1 - 4 correctly.
  • 1 reply
·
merve 
posted an update 8 days ago
view post
Post
2905
Apollo is a new family of open-source video language models by Meta, where 3B model outperforms most 7B models and 7B outperforms most 30B models 🧶

✨ the models come in 1.5B https://huggingface.co/Apollo-LMMs/Apollo-1_5B-t32, 3B https://huggingface.co/Apollo-LMMs/Apollo-3B-t32 and 7B https://huggingface.co/Apollo-LMMs/Apollo-7B-t32 with A2.0 license, based on Qwen1.5 & Qwen2
✨ the authors also release a benchmark dataset https://huggingface.co/spaces/Apollo-LMMs/ApolloBench

The paper has a lot of experiments (they trained 84 models!) about what makes the video LMs work ⏯️

Try the demo for best setup here https://huggingface.co/spaces/Apollo-LMMs/Apollo-3B
they evaluate sampling strategies, scaling laws for models and datasets, video representation and more!
> The authors find out that whatever design decision was applied to small models also scale properly when the model and dataset are scaled 📈 scaling dataset has diminishing returns for smaller models
> They evaluate frame sampling strategies, and find that FPS sampling is better than uniform sampling, and they find 8-32 tokens per frame optimal
> They also compare image encoders, they try a variation of models from shape optimized SigLIP to DINOv2
they find google/siglip-so400m-patch14-384 to be most powerful 🔥
> they also compare freezing different parts of models, training all stages with some frozen parts give the best yield

They eventually release three models, where Apollo-3B outperforms most 7B models and Apollo 7B outperforms 30B models 🔥
  • 3 replies
·
lucifertrj 
posted an update 11 days ago
view post
Post
483
Image Prompt Engineering Guide:
➡️ Artistic styling for Image generation
➡️ Prompt weighting using the parentheses method to generate realistic images.
➡️ Advanced features like style and positioning control[experimental].
➡️ Image placement on the generated AI image using Recraft V3 Mockup.

Watch: https://www.youtube.com/watch?v=d3nUG28-jIc
merve 
posted an update 13 days ago
view post
Post
1669
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
eienmojiki 
posted an update 14 days ago
view post
Post
1391
👀 Introducing 2048 Game API: A RESTful API for the Classic Puzzle Game 🧩

I'm excited to share my latest project, 2048 Game API, a RESTful API that allows you to create, manage, and play games of 2048, a popular puzzle game where players slide numbered tiles to combine them and reach the goal of getting a tile with the value of 2048.

⭐ Features
Create new games with customizable board sizes (3-8)
Make moves (up, down, left, right) and get the updated game state
Get the current game state, including the board, score, and game over status
Delete games
Generate images of the game board with customizable themes (light and dark)

🔗 API Endpoints
POST /api/games - Create a new game
GET /api/games/:gameId - Get the current game state
POST /api/games/:gameId/move - Make a move (up, down, left, right)
DELETE /api/games/:gameId - Delete a game
GET /api/games/:gameId/image - Generate an image of the game board

🧩 Example Use Cases
- Create a new game with a 4x4 board: 
curl -X POST -H "Content-Type: application/json" -d '{"size": 4}' http://localhost:3000/api/games

- Make a move up: 
curl -X POST -H "Content-Type: application/json" -d '{"direction": "up"}' http://localhost:3000/api/games/:gameId/move

- Get the current game state: 
curl -X GET http://localhost:3000/api/games/:gameId

💕 Try it out!
- Demo: eienmojiki/2048
- Source: https://github.com/kogakisaki/koga-2048
- You can try out the API by running the server locally or using a tool like Postman to send requests to the API. I hope you enjoy playing 2048 with this API!

Let me know if you have any questions or feedback!

🐧 Mouse1 is our friend🐧
sayakpaul 
posted an update 16 days ago
view post
Post
2040
Introducing a high-quality open-preference dataset to further this line of research for image generation.

Despite being such an inseparable component for modern image generation, open preference datasets are a rarity!

So, we decided to work on one with the community!

Check it out here:
https://huggingface.co/blog/image-preferences
·
shivi 
authored a paper 16 days ago
sayakpaul 
posted an update 16 days ago
view post
Post
2096
The Control family of Flux from @black-forest-labs should be discussed more!

It enables structural controls like ControlNets while being significantly less expensive to run!

So, we're working on a Control LoRA training script 🤗

It's still WIP, so go easy:
https://github.com/huggingface/diffusers/pull/10130
merve 
posted an update 17 days ago
view post
Post
5505
This week in open-source AI was insane 🤠 A small recap🕺🏻 merve/dec-6-releases-67545caebe9fc4776faac0a3

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

LLMs 💬
> 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 🔥
> 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! 🔥 nearly 8TB pretraining data in many languages!

Image/Video Generation 🖼️
> Tencent released HunyuanVideo, a new photorealistic video generation model
> OminiControl is a new editing/control framework for image generation models like Flux

Audio 🔊
> Indic-Parler-TTS is a new text2speech model made by community
merve 
posted an update 18 days ago
sayakpaul 
authored a paper 19 days ago
shivi 
authored 2 papers 19 days ago
Taylor658 
posted an update 23 days ago
view post
Post
433
🌐 The Stanford Institute for Human-Centered AI (https://aiindex.stanford.edu/vibrancy/) has released its 2024 Global AI Vibrancy Tool, a way to explore and compare AI progress across 36 countries.

📊 It measures progress across the 8 broad pillars of R&D, Responsible AI, Economy, Education, Diversity, Policy and Governance, Public Opinion and Infrastructure. (Each of these pillars have a number of Sub Indices)

📈 As a whole it is not surprising that the USA was at the top in terms of overall score as of 2023 (AI investment activity is a large part of the economic pillar for example and that is a large part of the overall USA ranking) but drilling in to more STRATEGIC Macro pillars like Education, Infrastructure or R&D reveal interesting growth patterns in Asia (particularly China) and Western Europe that I suspect the 2024 metrics will bear out.

🤖 Hopefully the 2024 Global Vibrancy ranking will break out AI and ML verticals like Computer Vision or NLP and or the AI Agent space as that may also from a global macro level give indications of what is to come globally for AI in 2025.
merve 
posted an update 23 days ago
view post
Post
2628
small but mighty 🔥
you can fine-tune SmolVLM on an L4 with batch size of 4 and it will only take 16.4 GB VRAM 🫰🏻 also with gradient accumulation simulated batch size is 16 ✨
I made a notebook that includes all the goodies: QLoRA, gradient accumulation, gradient checkpointing with explanations on how they work 💝 https://github.com/huggingface/smollm/blob/main/finetuning/Smol_VLM_FT.ipynb
merve 
posted an update 23 days ago
view post
Post
2864
Last week we were blessed with open-source models! A recap 💝
merve/nov-29-releases-674ccc255a57baf97b1e2d31

🖼️ Multimodal
> At Hugging Face 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
sayakpaul 
posted an update 26 days ago