162 169 191

Lain

not-lain

https://not-lain.github.io

AI & ML interests

custom AI models with HF integration, multimodal rag and open-source software

Articles

Organizations

not-lain's activity

upvoted 2 articles 5 days ago

Article

Docmatix - a huge dataset for Document Visual Question Answering

6 days ago

• 49

Article

TGI Multi-LoRA: Deploy Once, Serve 30 Models

6 days ago

• 29

upvoted 3 articles 7 days ago

Article

How we leveraged distilabel to create an Argilla 2.0 Chatbot

8 days ago

• 29

Article

Don't repeat yourself - 🤗 Transformers Design Philosophy

Apr 5, 2022

• 7

Article

SmolLM - blazingly fast and remarkably powerful

8 days ago

• 160

upvoted 5 articles 9 days ago

Article

How NuminaMath Won the 1st AIMO Progress Prize

13 days ago

• 74

Article

Train a Llama model from scratch

•

about 21 hours ago

• 25

Article

Proximal Policy Optimization (PPO)

Aug 5, 2022

• 7

Article

Introducing ⚔️ AI vs. AI ⚔️ a deep reinforcement learning multi-agents competition system

Feb 7, 2023

• 1

Article

Is AI carbon footprint worrisome?

•

9 days ago

• 3

upvoted an article 10 days ago

Article

Optimisation d'un système RAG pour la recherche sémantique

•

10 days ago

• 1

upvoted 2 articles 13 days ago

Article

Experimenting with Automatic PII Detection on the Hub using Presidio

14 days ago

• 20

Article

Announcing New Hugging Face and Keras NLP integration

14 days ago

• 25

upvoted 2 articles 15 days ago

Article

Announcing New Dataset Search Features

16 days ago

• 17

Article

Deploying 🤗 ViT on Vertex AI

Aug 19, 2022

• 2

upvoted an article 16 days ago

Article

_Repetita iuvant_: how to improve AI code generation

•

16 days ago

• 5

upvoted a paper 17 days ago

Expressive Gaussian Human Avatars from Monocular RGB Video

Paper • 2407.03204 • Published 20 days ago • 1

upvoted an article 17 days ago

Article

Training and Finetuning Embedding Models with Sentence Transformers v3

May 28

• 124

upvoted a paper 17 days ago

The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits

Paper • 2402.17764 • Published Feb 27 • 581

upvoted an article 17 days ago

Article

Our Transformers Code Agent beats the GAIA benchmark!

23 days ago

• 36

upvoted 2 collections 19 days ago

Arabic NLI & Semantic Similarity Datasets

Collection

The Arabic Version of SNLI and MultiNLI datasets, originally used for Natural Language Inference (NLI), may be used for finetuning embedding models. • 6 items • Updated Jun 18 • 3

Al-Baka Arabic LLAMA3 FineTuned Models

Collection

5 items • Updated Jun 17 • 2

upvoted an article 19 days ago

Article

EU Training Data Transparency: A Proposal for a Sufficiently Detailed Summary 📑📚🖼️🇪🇺

•

20 days ago

• 8

upvoted a collection 19 days ago

Arabic Matryoshka Embedding Models

Collection

A collection of advanced Arabic Matryoshka Embedding Models designed for efficient and high-performance Arabic NLP, available publicly on Hugging Face • 6 items • Updated 11 days ago • 6

upvoted a collection 20 days ago

InternLM2.5

Collection

7 items • Updated 5 days ago • 47

upvoted an article 21 days ago

Article

How I train a LoRA: m3lt style training overview

•

22 days ago

• 37

upvoted an article 25 days ago

Article

Formatting Datasets for Chat Template Compatibility

•

25 days ago

• 7

upvoted a collection 25 days ago

Gemma 2 Release

Collection

10 items • Updated 26 days ago • 130

upvoted an article 25 days ago

Article

Welcome Gemma 2 - Google's new open LLM

27 days ago

• 98

upvoted a collection 26 days ago

Probably DPO datasets

Collection

A collection of datasets that probably support DPO • 146 items • Updated 27 days ago • 8

upvoted a paper 27 days ago

The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale

Paper • 2406.17557 • Published 28 days ago • 75

upvoted 2 articles 28 days ago

Article

Faster fine-tuning using TRL & Unsloth

Jan 10

• 29

Article

Fine-tuning Florence-2 - Microsoft's Cutting-edge Vision Language Models

30 days ago

• 145

upvoted 2 papers 29 days ago

Visual Instruction Tuning

Paper • 2304.08485 • Published Apr 17, 2023 • 10

Improved Baselines with Visual Instruction Tuning

Paper • 2310.03744 • Published Oct 5, 2023 • 35

upvoted an article 29 days ago

Article

Uncensor any LLM with abliteration

•

Jun 13

• 239

upvoted an article about 1 month ago

Article

2D Asset Generation: AI for Game Development #4

Jan 26, 2023

• 1

upvoted a paper about 1 month ago

Zephyr: Direct Distillation of LM Alignment

Paper • 2310.16944 • Published Oct 25, 2023 • 120

upvoted a collection about 1 month ago

Depth-Anything-V2

Collection

6 items • Updated Jun 14 • 19

upvoted an article about 1 month ago

Article

Enhancing Image Model Dreambooth Training Through Effective Captioning: Key Observations

•

Jun 19

• 11

upvoted a paper about 1 month ago

How Do Large Language Models Acquire Factual Knowledge During Pretraining?

Paper • 2406.11813 • Published Jun 17 • 29

upvoted 3 collections about 1 month ago

CodeGemma Release

Collection

16 items • Updated 26 days ago • 70

MobileCLIP Models + DataCompDR Data

Collection

MobileCLIP: Mobile-friendly image-text models with SOTA zero-shot capabilities. DataCompDR: Improved datasets for training image-text SOTA models. • 22 items • Updated Jun 20 • 19

em🍞ing series

Collection

crispy sentence embedding family • 4 items • Updated 5 days ago • 20

upvoted a paper about 1 month ago

Scaling Rectified Flow Transformers for High-Resolution Image Synthesis

Paper • 2403.03206 • Published Mar 5 • 47

upvoted a collection about 2 months ago

Diffusion Tools

Collection

4 items • Updated Apr 30 • 3

upvoted 3 articles about 2 months ago

Article

BrAIn: next generation neurons?

•

Jun 5

• 15

Article

Hugging Face + Google Visual Blocks

•

May 16

• 21

Article

License to Call: Introducing Transformers Agents 2.0

May 13

• 102

upvoted a paper about 2 months ago

Quantum Embedding with Transformer for High-dimensional Data

Paper • 2402.12704 • Published Feb 20 • 2

upvoted an article about 2 months ago

Article

Fine-Tuning Gemma Models in Hugging Face

Feb 23

• 17

upvoted a paper 2 months ago

INDUS: Effective and Efficient Language Models for Scientific Applications

Paper • 2405.10725 • Published May 17 • 30

upvoted a collection 2 months ago

OS Week Highlights - Oct 9 - 15

Collection

17 items • Updated Jan 17 • 3

upvoted 3 articles 2 months ago

Article

What is going on with AlphaFold3?

•

May 21

• 8

Article

Welcome Llama 3 - Meta's new open LLM

Apr 18

• 263

Article

PaliGemma – Google's Cutting-Edge Open Vision Language Model

May 14

• 172

upvoted a paper 2 months ago

RAFT: Adapting Language Model to Domain Specific RAG

Paper • 2403.10131 • Published Mar 15 • 65

upvoted 3 articles 2 months ago

Article

Multimodal Augmentation for Documents: Recovering “Comprehension” in “Reading and Comprehension” task

•

May 16

• 15

Article

Introducing the Open Arabic LLM Leaderboard

May 14

• 56

Article

Hugging Face x LangChain : A new partner package in LangChain

May 14

• 94

Lain

AI & ML interests

Articles

RAG chatbot using llama3

Image-based search engine

Train custom AI models with the trainer API and adapt them to 🤗

Custom architectures with HuggingFace 🤗

Organizations

not-lain's activity

Docmatix - a huge dataset for Document Visual Question Answering

TGI Multi-LoRA: Deploy Once, Serve 30 Models

How we leveraged distilabel to create an Argilla 2.0 Chatbot

Don't repeat yourself - 🤗 Transformers Design Philosophy

SmolLM - blazingly fast and remarkably powerful

How NuminaMath Won the 1st AIMO Progress Prize

Train a Llama model from scratch

Proximal Policy Optimization (PPO)

Introducing ⚔️ AI vs. AI ⚔️ a deep reinforcement learning multi-agents competition system

Is AI carbon footprint worrisome?

Optimisation d'un système RAG pour la recherche sémantique

Experimenting with Automatic PII Detection on the Hub using Presidio

Announcing New Hugging Face and Keras NLP integration

Announcing New Dataset Search Features

Deploying 🤗 ViT on Vertex AI

_Repetita iuvant_: how to improve AI code generation

Training and Finetuning Embedding Models with Sentence Transformers v3

Our Transformers Code Agent beats the GAIA benchmark!

EU Training Data Transparency: A Proposal for a Sufficiently Detailed Summary 📑📚🖼️🇪🇺

How I train a LoRA: m3lt style training overview

Formatting Datasets for Chat Template Compatibility

Welcome Gemma 2 - Google's new open LLM

Faster fine-tuning using TRL & Unsloth

Fine-tuning Florence-2 - Microsoft's Cutting-edge Vision Language Models

Uncensor any LLM with abliteration

2D Asset Generation: AI for Game Development #4

Enhancing Image Model Dreambooth Training Through Effective Captioning: Key Observations

BrAIn: next generation neurons?

Hugging Face + Google Visual Blocks

License to Call: Introducing Transformers Agents 2.0

Fine-Tuning Gemma Models in Hugging Face

What is going on with AlphaFold3?

Welcome Llama 3 - Meta's new open LLM

PaliGemma – Google's Cutting-Edge Open Vision Language Model

Multimodal Augmentation for Documents: Recovering “Comprehension” in “Reading and Comprehension” task

Introducing the Open Arabic LLM Leaderboard

Hugging Face x LangChain : A new partner package in LangChain