Hugging Face's logo

HugGAN Community

non-profit
Activity Feed Request to join this org

AI & ML interests

GANs!

Recent Activity

gagan3012ย  authored a paper 5 days ago
DateLogicQA: Benchmarking Temporal Biases in Large Language Models
DrishtiSharmaย  authored a paper 13 days ago
1-800-SHARED-TASKS at RegNLP: Lexical Reranking of Semantic Retrieval (LeSeR) for Regulatory Question Answering
DrishtiSharmaย  authored a paper 14 days ago
Maya: An Instruction Finetuned Multilingual Multimodal Model
View all activity

huggan's activity

merveย 
posted an update 1 day ago
gagan3012ย 
authored a paper 5 days ago
merveย 
posted an update 7 days ago
view post
Post
2330
Aya by Cohere For AI can now see! ๐Ÿ‘€

C4AI community has built Maya 8B, a new open-source multilingual VLM built on SigLIP and Aya 8B ๐ŸŒฑ works on 8 languages! ๐Ÿ—ฃ๏ธ

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 ๐Ÿ‘
kudos @nahidalam and team
  • 1 reply
ยท
clemย 
posted an update 8 days ago
view post
Post
1527
Coming back to Paris Friday to open our new Hugging Face office!

We're at capacity for the party but add your name in the waiting list as we're trying to privatize the passage du Caire for extra space for robots ๐Ÿค–๐Ÿฆพ๐Ÿฆฟ

https://t.co/enkFXjWndJ
  • 1 reply
ยท
merveย 
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 ๐Ÿงถ

โœจ 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
โœจ 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 โฏ๏ธ

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 ๐Ÿ“ˆ 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 ๐Ÿ”ฅ
> 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 ๐Ÿ”ฅ
  • 3 replies
ยท
merveย 
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 ๐Ÿ““
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 ๐Ÿ”ฅ https://huggingface.co./learn/cookbook/multimodal_rag_using_document_retrieval_and_reranker_and_vlms
DrishtiSharmaย 
authored a paper 13 days ago
DrishtiSharmaย 
authored a paper 14 days ago
merveย 
posted an update 17 days ago
view post
Post
5505
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
merveย 
posted an update 18 days ago
view post
Post
1500
New InternVL drop with a state-of-the-art 78B vision language model with MIT license ๐Ÿ”ฅ https://huggingface.co./collections/OpenGVLab/internvl-25-673e1019b66e2218f68d7c1c
The release comes with seven new vision LMs based on InternViT 300M/6B and Qwen2.5 (0.5B, 3B, 32B, 72B) and InternLM2 (8B, 7B, 20B) in different sizes
78B model is of InternViT 6B and Qwen2.5-72B Instruct, can accomplish variety of tasks ๐Ÿ‘ Try here OpenGVLab/InternVL
DrishtiSharmaย 
authored 2 papers 21 days ago
merveย 
posted an update 23 days ago
view post
Post
2628
small but mighty ๐Ÿ”ฅ
you can fine-tune SmolVLM on an L4 with batch size of 4 and it will only take 16.4 GB VRAM ๐Ÿซฐ๐Ÿป also with gradient accumulation simulated batch size is 16 โœจ
I made a notebook that includes all the goodies: QLoRA, gradient accumulation, gradient checkpointing with explanations on how they work ๐Ÿ’ https://github.com/huggingface/smollm/blob/main/finetuning/Smol_VLM_FT.ipynb
clemย 
posted an update 23 days ago
view post
Post
4092
Six predictions for AI in 2025 (and a review of how my 2024 predictions turned out):

- There will be the first major public protest related to AI
- A big company will see its market cap divided by two or more because of AI
- At least 100,000 personal AI robots will be pre-ordered
- China will start to lead the AI race (as a consequence of leading the open-source AI race).
- There will be big breakthroughs in AI for biology and chemistry.
- We will begin to see the economic and employment growth potential of AI, with 15M AI builders on Hugging Face.

How my predictions for 2024 turned out:

- A hyped AI company will go bankrupt or get acquired for a ridiculously low price
โœ… (Inflexion, AdeptAI,...)

- Open-source LLMs will reach the level of the best closed-source LLMs
โœ… with QwQ and dozens of others

- Big breakthroughs in AI for video, time-series, biology and chemistry
โœ… for video ๐Ÿ”ดfor time-series, biology and chemistry

- We will talk much more about the cost (monetary and environmental) of AI
โœ…Monetary ๐Ÿ”ดEnvironmental (๐Ÿ˜ข)

- A popular media will be mostly AI-generated
โœ… with NotebookLM by Google

- 10 millions AI builders on Hugging Face leading to no increase of unemployment
๐Ÿ”œcurrently 7M of AI builders on Hugging Face
ยท
merveย 
posted an update 23 days ago
view post
Post
2864
Last week we were blessed with open-source models! A recap ๐Ÿ’
merve/nov-29-releases-674ccc255a57baf97b1e2d31

๐Ÿ–ผ๏ธ Multimodal
> At Hugging Face we released SmolVLM, a performant and efficient smol vision language model ๐Ÿ’—
> Show Lab released ShowUI-2B: new vision-language-action model to build GUI/web automation agents ๐Ÿค–
> 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 model๐Ÿ“–
> Dataset: LLaVA-CoT-100k dataset used to train Llava-CoT released by creators of Llava-CoT ๐Ÿ“•

๐Ÿ’ฌ LLMs
> Qwen team released QwQ-32B-Preview, state-of-the-art open-source reasoning model, broke the internet ๐Ÿ”ฅ
> AliBaba has released Marco-o1, a new open-source reasoning model ๐Ÿ’ฅ
> NVIDIA released Hymba 1.5B Base and Instruct, the new state-of-the-art SLMs with hybrid architecture (Mamba + transformer)

โฏ๏ธ 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 โฏ๏ธ
> Dataset: Image Preferences is a new image generation preference dataset made with DIBT community effort of Argilla ๐Ÿท๏ธ

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
DrishtiSharmaย 
authored a paper 23 days ago
clemย 
posted an update 25 days ago
view post
Post
4350
Hugging Face 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
ยท
merveย 
posted an update 28 days ago
view post
Post
2161
The authors of ColPali trained a retrieval model based on SmolVLM ๐Ÿค  vidore/colsmolvlm-alpha
TLDR;

- ColSmolVLM performs better than ColPali and DSE-Qwen2 on all English tasks

- ColSmolVLM is more memory efficient than ColQwen2 ๐Ÿ’—
merveย 
posted an update 29 days ago
view post
Post
3870
Small yet mighty! ๐Ÿ’ซ

We are releasing SmolVLM: a new 2B small vision language made for on-device use, fine-tunable on consumer GPU, immensely memory efficient ๐Ÿค 

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 ๐Ÿ’
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 ๐Ÿ’—
clemย 
posted an update about 1 month ago
view post
Post
1971
I've been in Brazil for 10 days now ๐Ÿ‡ง๐Ÿ‡ท๐Ÿ‡ง๐Ÿ‡ท๐Ÿ‡ง๐Ÿ‡ท

I've been surprised by the gap between the massive number of people interested in AI (chatgpt adoption is crazy here) and the relatively low number of real AI builders - aka people and companies building their own AI models, datasets and apps.

Lots of efforts needed across the world for everyone to participate, control and benefit this foundational technology, starting with open-source & multi-lingual AI, more access to GPUs & AI builder training for all!