lunarflu (Adam Molnar)

upvoted 3 articles 4 days ago

Article

Image-based search engine

By

•

5 days ago

• 20

Article

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

By

•

6 days ago

• 7

Article

How I train a LoRA: m3lt style training overview

By

•

8 days ago

• 23

upvoted a paper 6 days ago

HuggingFace's Transformers: State-of-the-art Natural Language Processing

Paper • 1910.03771 • Published Oct 9, 2019 • 16

upvoted a collection 7 days ago

Gemma 2 Release

Collection

10 items • Updated 12 days ago • 114

upvoted 4 articles 8 days ago

Article

BM25 for Python: Achieving high performance while simplifying dependencies with BM25S⚡

By

•

about 3 hours ago

• 25

Article

Build Agentic Workflow using OpenAGI and HuggingFace models

By

•

13 days ago

• 6

Article

Tokenization Is A Dead Weight

By

•

12 days ago

• 11

Article

Financial Analysis with Langchain and CrewAI Agents

By

•

9 days ago

• 4

upvoted an article 12 days ago

Article

Welcome Gemma 2 - Google's new open LLM

12 days ago

• 86

upvoted an article 14 days ago

Article

Data Is Better Together: A Look Back and Forward

19 days ago

• 15

upvoted 5 articles 18 days ago

Article

Thoughts on LoRA Training #1

By

•

21 days ago

• 28

Article

Thoughts on LoRA Training Pt 2: Where to Train

By

•

21 days ago

• 9

Article

Train a Terrible Tic-Tac-Toe AI

By

•

21 days ago

• 3

Article

Enhancing Image Model Dreambooth Training Through Effective Captioning: Key Observations

By

•

20 days ago

• 11

Article

Introducing Synthetic Data Workshop: Your Gateway to Easy Synthetic Dataset Creation

By

•

19 days ago

• 11

upvoted an article 19 days ago

Article

Unveiling CIVICS: A New Dataset for Examining Cultural Values in Language Models

By

•

20 days ago

• 7

upvoted 2 collections 21 days ago

DeepSeek-Coder

Collection

DeepSeek Coder series • 8 items • Updated Mar 26 • 36

DeepSeekCoder-V2

Collection

4 items • Updated 25 days ago • 57

upvoted 5 articles 26 days ago

Article

Extracting Concepts from LLMs: Anthropic’s recent discoveries 📖

By

•

19 days ago

• 25

Article

MobileNet-V4 (now in timm)

By

•

22 days ago

• 30

Article

An Optimal Lossy Variant of Speculative Decoding

By

•

26 days ago

• 1

Article

Low Latency CPU Based Educational Value Classifier With Generic Educational Value

By

•

26 days ago

• 7

Article

An Analysis of Chinese LLM Censorship and Bias with Qwen 2 Instruct

By

•

28 days ago

• 41

upvoted a collection 26 days ago

SimCLRv1 PyTorch Weights

Collection

Official PyTorch converted weights of SimCLRv1 • 4 items • Updated 27 days ago • 1

upvoted 3 articles 27 days ago

Article

Putting RL back in RLHF

27 days ago

• 53

Article

How do Textual Inversion tokens destroy prompts?

By

•

Mar 31

• 2

Article

RAG chatbot using llama3

By

•

1 day ago

• 47

upvoted an article 28 days ago

Article

Introducing the Hugging Face Embedding Container for Amazon SageMaker

Jun 7

• 11

upvoted a paper 29 days ago

MAmmoTH2: Scaling Instructions from the Web

Paper • 2405.03548 • Published May 6 • 6

upvoted 15 articles about 1 month ago

Article

Uncensor any LLM with abliteration

By

•

26 days ago

• 230

Article

BrAIn: next generation neurons?

By

•

Jun 5

• 15

Article

Sales Forecasting with Image Regression

By

•

May 24

• 5

Article

Faster assisted generation support for Intel Gaudi

Jun 4

• 3

Article

Orquestrando Small Language Models (SLM) usando JavaScript e a API de Inferência do Hugging Face

By

•

Jun 4

• 1

Article

Orchestrating Small Language Models (SLM) using JavaScript and the Hugging Face Inference API

By

•

Jun 4

• 1

Article

FaceChain-FACT: Open-source 10-second portrait generation, reusing massive LoRa styles, a base-model-friendly portrait application.

By

•

May 31

• 1

Article

Introducing UNA-ThePitbull Series

By

•

Jun 1

• 2

Article

Formatting Datasets for Chat Template Compatibility

By

•

10 days ago

• 6

Article

Fine-tuning LLMs with Singular Value Decomposition

By

•

Jun 2

• 7

Article

Space secrets security update

May 31

• 50

Article

Fine-tuning Mistral on Your Dataset

By

•

6 days ago

• 6

Article

Fine Tuning TinyLlama for Text Generation with TRL

By

•

10 days ago

• 3

Article

FiftyOne Computer Vision Datasets Come to the Hugging Face Hub

By

•

Jun 3

• 11

Article

Orchestration of Experts: The First-Principle Multi-Model System

By

•

May 30

• 14

upvoted 7 papers about 1 month ago

3DitScene: Editing Any Scene via Language-guided Disentangled Gaussian Splatting

Paper • 2405.18424 • Published May 28 • 7

VeLoRA: Memory Efficient Training using Rank-1 Sub-Token Projections

Paper • 2405.17991 • Published May 28 • 9

LLaMA-NAS: Efficient Neural Architecture Search for Large Language Models

Paper • 2405.18377 • Published May 28 • 16

Instruct-MusicGen: Unlocking Text-to-Music Editing for Music Language Models via Instruction Tuning

Paper • 2405.18386 • Published May 28 • 17

upvoted an article about 1 month ago

Article

⚗️ 🔥 Building High-Quality Datasets with distilabel and Prometheus 2

By

•

Jun 3

• 21

upvoted 5 articles about 2 months ago

Article

Journey With Me Into The Mind of Large Language Models: Interesting Findings in AnthropicAI's Scaling Monosemanticity paper.

By

•

May 22

• 2

Article

Synthetic dataset generation techniques: generating custom sentence similarity data

By

•

May 23

• 13

Article

Let's talk about LLM evaluation

By

•

May 23

• 93

Article

Training MoE on AWS Trainium

By

•

May 23

• 4

Article

Virtual Try-On using IP-Adapter Inpainting

By

•

Jun 4

• 14

upvoted a paper about 2 months ago

MindEye2: Shared-Subject Models Enable fMRI-To-Image With 1 Hour of Data

Paper • 2403.11207 • Published Mar 17 • 14

upvoted an article about 2 months ago

Article

Enjoy the Power of Phi-3 with ONNX Runtime on your device

By

•

May 22

• 22

Adam Molnar

AI & ML interests

Organizations

lunarflu's activity

Image-based search engine

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

How I train a LoRA: m3lt style training overview

BM25 for Python: Achieving high performance while simplifying dependencies with *BM25S*⚡

Build Agentic Workflow using OpenAGI and HuggingFace models

Tokenization Is A Dead Weight

Financial Analysis with Langchain and CrewAI Agents

Welcome Gemma 2 - Google's new open LLM

Data Is Better Together: A Look Back and Forward

Thoughts on LoRA Training #1

Thoughts on LoRA Training Pt 2: Where to Train

Train a Terrible Tic-Tac-Toe AI

Enhancing Image Model Dreambooth Training Through Effective Captioning: Key Observations

Introducing Synthetic Data Workshop: Your Gateway to Easy Synthetic Dataset Creation

Unveiling CIVICS: A New Dataset for Examining Cultural Values in Language Models

Extracting Concepts from LLMs: Anthropic’s recent discoveries 📖

MobileNet-V4 (now in timm)

An Optimal Lossy Variant of Speculative Decoding

Low Latency CPU Based Educational Value Classifier With Generic Educational Value

An Analysis of Chinese LLM Censorship and Bias with Qwen 2 Instruct

Putting RL back in RLHF

How do Textual Inversion tokens destroy prompts?

RAG chatbot using llama3

Introducing the Hugging Face Embedding Container for Amazon SageMaker

Uncensor any LLM with abliteration

BrAIn: next generation neurons?

Sales Forecasting with Image Regression

Faster assisted generation support for Intel Gaudi

Orquestrando Small Language Models (SLM) usando JavaScript e a API de Inferência do Hugging Face

Orchestrating Small Language Models (SLM) using JavaScript and the Hugging Face Inference API

FaceChain-FACT: Open-source 10-second portrait generation, reusing massive LoRa styles, a base-model-friendly portrait application.

Introducing UNA-ThePitbull Series

Formatting Datasets for Chat Template Compatibility

Fine-tuning LLMs with Singular Value Decomposition

Space secrets security update

Fine-tuning Mistral on Your Dataset

Fine Tuning TinyLlama for Text Generation with TRL

FiftyOne Computer Vision Datasets Come to the Hugging Face Hub

Orchestration of Experts: The First-Principle Multi-Model System

⚗️ 🔥 Building High-Quality Datasets with distilabel and Prometheus 2

Journey With Me Into The Mind of Large Language Models: Interesting Findings in AnthropicAI's Scaling Monosemanticity paper.

Synthetic dataset generation techniques: generating custom sentence similarity data

Let's talk about LLM evaluation

Training MoE on AWS Trainium

Virtual Try-On using IP-Adapter Inpainting

Enjoy the Power of Phi-3 with ONNX Runtime on your device

BM25 for Python: Achieving high performance while simplifying dependencies with BM25S⚡