Gradio-Themes-Party

company

AI & ML interests

None defined yet.

Recent Activity

Gradio-Themes's activity

AtAndDevย 
posted an update 7 days ago
view post
Post
298
@s3nh Hey man check your discord! Got some news.
  • 4 replies
ยท
louisbrulenaudetย 
posted an update about 1 month ago
view post
Post
1728
Iโ€™ve published a new dataset to simplify model merging ๐Ÿค—

This dataset facilitates the search for compatible architectures for model merging with @arcee_aiโ€™s mergekit, streamlining the automation of high-performance merge searches ๐Ÿ“–

Dataset : louisbrulenaudet/mergekit-configs
  • 1 reply
ยท
louisbrulenaudetย 
posted an update about 2 months ago
view post
Post
1139
Introducing Lemone-router, a series of classification models designed to produce an optimal multi-agent system for different branches of tax law.

Trained on a base of 49k lines comprising a set of synthetic questions generated by GPT-4 Turbo and Llama 3.1 70B, which have been further refined through evol-instruction tuning and manual curation and authority documents, these models are based on an 8-category decomposition of the classification scheme derived from the Bulletin officiel des finances publiques - impรดts :

label2id = {
    "Bรฉnรฉfices professionnels": 0,
    "Contrรดle et contentieux": 1,
    "Dispositifs transversaux": 2,
    "Fiscalitรฉ des entreprises": 3,
    "Patrimoine et enregistrement": 4,
    "Revenus particuliers": 5,
    "Revenus patrimoniaux": 6,
    "Taxes sur la consommation": 7
}
	
id2label = {
    0: "Bรฉnรฉfices professionnels",
    1: "Contrรดle et contentieux",
    2: "Dispositifs transversaux",
    3: "Fiscalitรฉ des entreprises",
    4: "Patrimoine et enregistrement",
    5: "Revenus particuliers",
    6: "Revenus patrimoniaux",
    7: "Taxes sur la consommation"
}

It achieves the following results on the evaluation set:
- Loss: 0.4734
- Accuracy: 0.9191

Link to the collection: louisbrulenaudet/lemone-router-671cce21d6410f3570514762
louisbrulenaudetย 
posted an update 2 months ago
view post
Post
3105
๐Ÿšจ I have $3,500 in Azure credits, including access to an H100 (96 Go), expiring on November 12, 2024.

I wonโ€™t be able to use it all myself, so Iโ€™m reaching out to the @huggingface community: Are there any open-source projets with data ready for some compute power?

Letโ€™s collaborate and make the most of it together ๐Ÿ”—
ยท
louisbrulenaudetย 
posted an update 3 months ago
view post
Post
2099
My biggest release of the year: a series of 7 specialized embedding models for information retrieval within tax documents, is now available for free on Hugging Face ๐Ÿค—

These new models aim to offer an open source alternative for in-domain semantic search from largeย text corpora and will improve RAG systems and context addition for large language models.

Trained on more than 43 million tax tokens derived from semi-synthetic and raw-synthetic data, enriched by various methods (in particular MSFT's evol-instruct by @intfloat ), and corrected by humans, this project is the fruit of hundreds of hours of work and is the culmination of a global effort to open up legal technologies that has only just begun.

A big thank you to Microsoft for Startups for giving me access to state-of-the-art infrastructure to train these models, and to @julien-c , @clem ๐Ÿค—, @thomwolf and the whole HF team for the inference endpoint API and the generous provision of Meta LLama-3.1-70B. Special thanks also to @tomaarsen for his invaluable advice on training embedding models and Loss functions โค๏ธ

Models are available on my personal HF page, into the Lemone-embed collection: louisbrulenaudet/lemone-embed-66fdc24000df732b395df29b
  • 1 reply
ยท
DmitryRyuminย 
posted an update 3 months ago
view post
Post
2605
๐Ÿ”ฅ๐ŸŽญ๐ŸŒŸ New Research Alert - HeadGAP (Avatars Collection)! ๐ŸŒŸ๐ŸŽญ๐Ÿ”ฅ
๐Ÿ“„ Title: HeadGAP: Few-shot 3D Head Avatar via Generalizable Gaussian Priors ๐Ÿ”

๐Ÿ“ Description: HeadGAP introduces a novel method for generating high-fidelity, animatable 3D head avatars from few-shot data, using Gaussian priors and dynamic part-based modelling for personalized and generalizable results.

๐Ÿ‘ฅ Authors: @zxz267 , @walsvid , @zhaohu2 , Weiyi Zhang, @hellozhuo , Xu Chang, Yang Zhao, Zheng Lv, Xiaoyuan Zhang, @yongjie-zhang-mail , Guidong Wang, and Lan Xu

๐Ÿ“„ Paper: HeadGAP: Few-shot 3D Head Avatar via Generalizable Gaussian Priors (2408.06019)

๐ŸŒ Github Page: https://headgap.github.io

๐Ÿš€ CVPR-2023-24-Papers: https://github.com/DmitryRyumin/CVPR-2023-24-Papers

๐Ÿš€ WACV-2024-Papers: https://github.com/DmitryRyumin/WACV-2024-Papers

๐Ÿš€ ICCV-2023-Papers: https://github.com/DmitryRyumin/ICCV-2023-Papers

๐Ÿ“š More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin

๐Ÿš€ Added to the Avatars Collection: DmitryRyumin/avatars-65df37cdf81fec13d4dbac36

๐Ÿ” Keywords: #HeadGAP #3DAvatar #FewShotLearning #GaussianPriors #AvatarCreation #3DModeling #MachineLearning #ComputerVision #ComputerGraphics #GenerativeAI #DeepLearning #AI
DmitryRyuminย 
posted an update 3 months ago
view post
Post
2046
๐Ÿš€๐Ÿ•บ๐ŸŒŸ New Research Alert - ECCV 2024 (Avatars Collection)! ๐ŸŒŸ๐Ÿ’ƒ๐Ÿš€
๐Ÿ“„ Title: Expressive Whole-Body 3D Gaussian Avatar ๐Ÿ”

๐Ÿ“ Description: ExAvatar is a model that generates animatable 3D human avatars with facial expressions and hand movements from short monocular videos using a hybrid mesh and 3D Gaussian representation.

๐Ÿ‘ฅ Authors: Gyeongsik Moon, Takaaki Shiratori, and @psyth

๐Ÿ“… Conference: ECCV, 29 Sep โ€“ 4 Oct, 2024 | Milano, Italy ๐Ÿ‡ฎ๐Ÿ‡น

๐Ÿ“„ Paper: MeshAvatar: Learning High-quality Triangular Human Avatars from Multi-view Videos (2407.08414)

๐Ÿ“„ Paper: Expressive Whole-Body 3D Gaussian Avatar (2407.21686)

๐ŸŒ Github Page: https://mks0601.github.io/ExAvatar
๐Ÿ“ Repository: https://github.com/mks0601/ExAvatar_RELEASE

๐Ÿš€ CVPR-2023-24-Papers: https://github.com/DmitryRyumin/CVPR-2023-24-Papers

๐Ÿš€ WACV-2024-Papers: https://github.com/DmitryRyumin/WACV-2024-Papers

๐Ÿš€ ICCV-2023-Papers: https://github.com/DmitryRyumin/ICCV-2023-Papers

๐Ÿ“š More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin

๐Ÿš€ Added to the Avatars Collection: DmitryRyumin/avatars-65df37cdf81fec13d4dbac36

๐Ÿ” Keywords: #ExAvatar #3DAvatar #FacialExpressions #HandMotions #MonocularVideo #3DModeling #GaussianSplatting #MachineLearning #ComputerVision #ComputerGraphics #DeepLearning #AI #ECCV2024
DmitryRyuminย 
posted an update 3 months ago
view post
Post
1854
๐Ÿ”ฅ๐ŸŽญ๐ŸŒŸ New Research Alert - ECCV 2024 (Avatars Collection)! ๐ŸŒŸ๐ŸŽญ๐Ÿ”ฅ
๐Ÿ“„ Title: MeshAvatar: Learning High-quality Triangular Human Avatars from Multi-view Videos ๐Ÿ”

๐Ÿ“ Description: MeshAvatar is a novel pipeline that generates high-quality triangular human avatars from multi-view videos, enabling realistic editing and rendering through a mesh-based approach with physics-based decomposition.

๐Ÿ‘ฅ Authors: Yushuo Chen, Zerong Zheng, Zhe Li, Chao Xu, and Yebin Liu

๐Ÿ“… Conference: ECCV, 29 Sep โ€“ 4 Oct, 2024 | Milano, Italy ๐Ÿ‡ฎ๐Ÿ‡น

๐Ÿ“„ Paper: MeshAvatar: Learning High-quality Triangular Human Avatars from Multi-view Videos (2407.08414)

๐ŸŒ Github Page: https://shad0wta9.github.io/meshavatar-page
๐Ÿ“ Repository: https://github.com/shad0wta9/meshavatar

๐Ÿ“บ Video: https://www.youtube.com/watch?v=Kpbpujkh2iI

๐Ÿš€ CVPR-2023-24-Papers: https://github.com/DmitryRyumin/CVPR-2023-24-Papers

๐Ÿš€ WACV-2024-Papers: https://github.com/DmitryRyumin/WACV-2024-Papers

๐Ÿš€ ICCV-2023-Papers: https://github.com/DmitryRyumin/ICCV-2023-Papers

๐Ÿ“š More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin

๐Ÿš€ Added to the Avatars Collection: DmitryRyumin/avatars-65df37cdf81fec13d4dbac36

๐Ÿ” Keywords: #MeshAvatar #3DAvatars #MultiViewVideo #PhysicsBasedRendering #TriangularMesh #AvatarCreation #3DModeling #NeuralRendering #Relighting #AvatarEditing #MachineLearning #ComputerVision #ComputerGraphics #DeepLearning #AI #ECCV2024