Hugging Face's logo

Hugging Face for Computer Vision

community
Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

sezan92Β  new activity 12 days ago
hf-vision/course-assets:vt-0-arch
mmhamdyΒ  authored a paper 19 days ago
Bridging the Data Provenance Gap Across Text, Speech and Video
qubvel-hfΒ  new activity about 1 month ago
hf-vision/object_detection_leaderboard:🚩 Leaderboard down!
View all activity

hf-vision's activity

merveΒ 
posted an update about 19 hours ago
view post
Post
690
Everything that happened this week in open AI, a recap 🀠 merve/jan-17-releases-678a673a9de4a4675f215bf5

πŸ‘€ 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

πŸ’¬ LLMs
- MiniMax-Text-01 is a new huge language model (456B passive 45.9B active params) by MiniMaxAI with context length of 4M tokens 🀯
- 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 πŸ§™πŸ»β€β™‚οΈ
- 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

πŸ–ΌοΈ Vision
- MatchAnything is a new foundation model for matching
- FitDit is a high-fidelity VTON model based on DiT architecture

πŸ—£οΈ Audio
- OuteTTS-0.3-1B is a new multilingual text-to-speech model with voice cloning and emotion control capabilities

πŸ“– 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
merveΒ 
posted an update 1 day ago
merveΒ 
posted an update 5 days ago
view post
Post
3779
there's a new multimodal retrieval model in town 🀠
LlamaIndex released vdr-2b-multi-v1
> uses 70% less image tokens, yet outperforming other dse-qwen2 based models
> 3x faster inference with less VRAM πŸ’¨
> shrinkable with matryoshka πŸͺ†
> can do cross-lingual retrieval!
Collection: llamaindex/visual-document-retrieval-678151d19d2758f78ce910e1 (with models and datasets)
Demo: llamaindex/multimodal_vdr_demo
Learn more from their blog post here https://huggingface.co/blog/vdr-2b-multilingual πŸ“–
merveΒ 
posted an update 8 days ago
view post
Post
3540
What a beginning to this year in open ML 🀠
Let's unwrap! merve/jan-10-releases-677fe34177759de0edfc9714

Multimodal πŸ–ΌοΈ
> ByteDance released SA2VA: a family of vision LMs that can take image, video, text and visual prompts
> moondream2 is out with new capabilities like outputting structured data and gaze detection!
> Dataset: Alibaba DAMO lab released multimodal textbook β€” 22k hours worth of samples from instruction videos 🀯
> Dataset: SciCap captioning on scientific documents benchmark dataset is released along with the challenge!

LLMs πŸ’¬
> Microsoft released Phi-4, sota open-source 14B language model πŸ”₯
> Dolphin is back with Dolphin 3.0 Llama 3.1 8B 🐬🐬
> Prime-RL released Eurus-2-7B-PRIME a new language model trained using PRIME alignment
> SmallThinker-3B is a new small reasoning LM based on Owen2.5-3B-Instruct πŸ’­
> Dataset: QWQ-LONGCOT-500K is the dataset used to train SmallThinker, generated using QwQ-32B-preview πŸ“•
> Dataset: @cfahlgren1 released React Code Instructions: a dataset of code instruction-code pairs πŸ“•
> Dataset: Qwen team is on the roll, they just released CodeElo, a dataset of code preferences πŸ‘©πŸ»β€πŸ’»

Embeddings πŸ”–
> @MoritzLaurer released zero-shot version of ModernBERT large πŸ‘
> KaLM is a new family of performant multilingual embedding models with MIT license built using Qwen2-0.5B

Image/Video Generation ⏯️
> NVIDIA released Cosmos, a new family of diffusion/autoregressive World Foundation Models generating worlds from images, videos and texts πŸ”₯
> Adobe released TransPixar: a new text-to-video model that can generate assets with transparent backgrounds (a first!)
> Dataset: fal released cosmos-openvid-1m Cosmos-tokenized OpenVid-1M with samples from OpenVid-1M

Others
> Prior Labs released TabPFNv2, the best tabular transformer is out for classification and regression
> Metagene-1 is a new RNA language model that can be used for pathogen detection, zero-shot embedding and genome understanding
merveΒ 
posted an update 9 days ago
view post
Post
1746
ByteDance just dropped SA2VA: a new family of vision LMs combining Qwen2VL/InternVL and SAM2 with MIT license πŸ’— ByteDance/sa2va-model-zoo-677e3084d71b5f108d00e093

> The models are capable of tasks involving vision-language understanding and visual referrals (referring segmentation) both for images and videos ⏯️

> The models come in 1B, 4B and 8B and are based on InternVL2.5 for base architecture and Qwen2, Qwen2.5 and InternLM2 for language model part (depending on the checkpoint)

> The model is very interesting, it has different encoders for different modalities each (visual prompt, text prompt, image and video) then it concatenates these to feed into LLM πŸ’¬

the output segmentation tokens are passed to SAM2, to sort of match text (captions or semantic classes) to masks ‡️

> Their annotation pipeline is also interesting, they seems to use two open large vision LMs to refine the annotations, and have different levels of descriptions to provide consistency.
  • 1 reply
Β·
sezan92Β 
in hf-vision/course-assets 12 days ago

vt-0-arch
#95 opened 12 days ago by
sezan92
merveΒ 
posted an update 18 days ago
view post
Post
4782
supercharge your LLM apps with smolagents πŸ”₯

however cool your LLM is, without being agentic it can only go so far

enter smolagents: a new agent library by Hugging Face to make the LLM write code, do analysis and automate boring stuff!

Here's our blog for you to get started https://huggingface.co/blog/smolagents
mmhamdyΒ 
authored a paper 19 days ago
merveΒ 
posted an update 25 days ago
merveΒ 
posted an update about 1 month ago
view post
Post
2798
Aya by Cohere For AI can now see! πŸ‘€

C4AI community has built Maya 8B, a new open-source multilingual VLM built on SigLIP and Aya 8B 🌱 works on 8 languages! πŸ—£οΈ

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 πŸ‘
kudos @nahidalam and team
  • 1 reply
Β·
qubvel-hfΒ 
in hf-vision/object_detection_leaderboard about 1 month ago

🚩 Leaderboard down!

1
#4 opened about 2 months ago by
alvarobartt
qubvel-hfΒ 
in hf-vision/finetuning_demo_for_object_detection about 1 month ago

Update README.md
#1 opened about 1 month ago by
qubvel-hf
qubvel-hfΒ 
updated a Space about 1 month ago
qubvel-hfΒ 
in hf-vision/nougat-transformers about 1 month ago

Update README.md
#3 opened about 1 month ago by
qubvel-hf
qubvel-hfΒ 
updated a Space about 1 month ago
merveΒ 
posted an update about 1 month ago
view post
Post
3348
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 πŸ“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 πŸ”₯
> 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 πŸ”₯
Β·
asusevskiΒ 
authored a paper about 1 month ago
celinahΒ 
posted an update about 1 month ago
view post
Post
622
πŸš€ We've just dropped a new release v0.27.0 of the πš‘πšžπšπšπš’πš—πšπšπšŠπšŒπšŽ_πš‘πšžπš‹ Python library!

This release includes:
- πŸ’Ύ New torch model loading utilities in the serialization module β€” providing a standardized way to save and load torch models with built-in support for sharding and safe serialization.
- πŸ“¦ Tooling for something exciting β€” if you like single-file formats for models like GGUF, you'll love what we're cooking up πŸ‘€ More coming soon!
- πŸ› οΈ Loads of quality-of-life improvements and bug fixes!

release notes and full details here πŸ‘‡
Wauplin/huggingface_hub#10

$ pip install -U huggingface_hub
merveΒ 
posted an update about 1 month ago
view post
Post
1773
A complete RAG pipeline includes a reranker, which ranks the documents to find the best document πŸ““
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 πŸ”₯ https://huggingface.co/learn/cookbook/multimodal_rag_using_document_retrieval_and_reranker_and_vlms
SuryaKrishna02Β 
authored a paper about 1 month ago