lunarflu (Adam Molnar)

upvoted 3 articles 1 day ago

Article

Perspectives for first principles prompt engineering

By

•

6 days ago

• 16

Article

dstack: Your LLM Launchpad - From Fine-Tuning to Serving, Simplified

By

•

3 days ago

• 12

Article

How to communicate in a Pull Request?

By

•

2 days ago

• 15

upvoted 11 articles 3 days ago

Article

Using Writer Framework with Hugging Face Spaces

By

•

4 days ago

• 29

Article

What are Embeddings and Vector Databases?

By

•

4 days ago

• 2

Article

Extractive Question Answering with AutoTrain

By

•

4 days ago

• 10

Article

How to get GPT to talk like a consultant

By

•

4 days ago

• 3

Article

Web Scraping 102

By

•

4 days ago

• 1

Article

Self-Hosting LLaMA 3.1 70B (or any ~70B LLM) Affordably

By

•

4 days ago

• 1

Article

Tensor Parallelism

By

•

5 days ago

• 7

Article

Web Scraping 101

By

•

5 days ago

• 3

Article

Llama-3.1-Storm-8B: Improved SLM with Self-Curation + Model Merging

By

•

5 days ago

• 56

Article

∞🧙🏼‍♂️AnyClassifier - Generating Synthetic Data For Text Classification

By

•

5 days ago

• 6

Article

Data Formats 101

By

•

5 days ago

• 1

upvoted 4 articles 5 days ago

Article

Processing Parquets 101

By

•

5 days ago

• 1

Article

Outperforming Claude 3.5 Sonnet with Phi-3-mini-4k for graph entity relationship extraction tasks

By

•

5 days ago

• 5

Article

I Trained a 2D Game Animation Generation Model to Create Complex, Cool Game Actions (Fully Open-Source)

By

•

6 days ago

• 4

Article

BERT for Bias Detection in Text

By

•

7 days ago

• 2

upvoted 2 articles 9 days ago

Article

The Workflow of PEFT

By

•

10 days ago

• 18

Article

Context Parallelism

By

•

11 days ago

• 3

upvoted 3 articles 11 days ago

Article

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

May 14

• 191

Article

2024 Security Feature Highlights

19 days ago

• 9

Article

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

Jun 24

• 160

upvoted 5 articles 16 days ago

Article

The case for specialized pre-training: ultra-fast foundation models for dedicated tasks

By

•

20 days ago

• 24

Article

Agentic Task Delegation - Making Agents whole again

By

•

19 days ago

• 3

Article

ArabicWeb24: Creating a High Quality Arabic Web-only Pre-training Dataset

By

•

16 days ago

• 8

Article

Batch size 30 AdamW vs Batch Size 1 Adafactor SDXL Training Comparison

By

•

16 days ago

• 2

Article

Unlocking Creativity with Text-to-Image Generation: Exploring LoRA Models and Styles

By

•

16 days ago

• 7

upvoted 2 articles 18 days ago

Article

Google releases Gemma 2 2B, ShieldGemma and Gemma Scope

25 days ago

• 57

Article

Introducing TextImage Augmentation for Document Images

19 days ago

• 24

upvoted a collection 19 days ago

MambaVision

Collection

MambaVision: A Hybrid Mamba-Transformer Vision Backbone. Includes tiny, tiny2, small, base, large and large2 variants. • 8 items • Updated Jul 24 • 11

upvoted a paper 20 days ago

Gemma 2: Improving Open Language Models at a Practical Size

Paper • 2408.00118 • Published 24 days ago • 72

upvoted a collection 22 days ago

InternLM2-Reward

Collection

InternLM2 Reward Models • 3 items • Updated Jul 19 • 3

upvoted 2 articles 22 days ago

Article

SmolLM - blazingly fast and remarkably powerful

Jul 16

• 225

Article

Introducing IDEFICS: An Open Reproduction of State-of-the-art Visual Language Model

Aug 22, 2023

• 18

upvoted a collection 22 days ago

H2O Danube3

Collection

6 items • Updated Jul 16 • 50

upvoted 3 articles 23 days ago

Article

Fine-tune Llama 3.1 Ultra-Efficiently with Unsloth

By

•

26 days ago

• 164

Article

Build static HTML spaces

By

•

25 days ago

• 5

Article

🔥 Argilla 2.0: the data-centric tool for AI makers 🤗

By

•

25 days ago

• 31

upvoted 2 articles 25 days ago

Article

Serverless Inference with Hugging Face and NVIDIA NIMs

27 days ago

• 20

Article

LAVE: Zero-shot VQA Evaluation on Docmatix with LLMs - Do We Still Need Fine-Tuning?

about 1 month ago

• 17

upvoted 6 articles 29 days ago

Article

ZebraLogic: Benchmarking the Logical Reasoning Ability of Language Models

By

•

28 days ago

• 21

Article

Are We Ready for Multi-Image Reasoning? Launching VHs: The Visual Haystacks Benchmark!

By

•

Jul 23

• 2

Article

Announcing BigCodeBench-Hard, and More

By

•

about 1 month ago

• 10

Article

Clarity AI Upscaler Reproduction

By

•

25 days ago

• 15

Article

Finetuning PaliGemma with AutoTrain

By

•

about 1 month ago

• 7

Article

Abliterating Refusal and Code LLMs

By

•

29 days ago

• 1

upvoted 13 articles about 1 month ago

Article

Llama 3.1 - 405B, 70B & 8B with multilinguality and long context

Jul 23

• 168

Article

How NuminaMath Won the 1st AIMO Progress Prize

Jul 11

• 84

Article

The Rise of Agentic Data Generation

By

•

Jul 15

• 73

Article

Taxonomy Completion with Embedding Quantization and an LLM-based Pipeline: A Case Study in Computational Linguistics

By

•

Jul 22

• 3

Article

Preference Optimization for Vision Language Models

Jul 10

• 30

Article

Experimenting with Automatic PII Detection on the Hub using Presidio

Jul 10

• 23

Article

Announcing New Hugging Face and Keras NLP integration

Jul 10

• 27

Article

How we leveraged distilabel to create an Argilla 2.0 Chatbot

Jul 16

• 30

Article

Enhancing Search Capabilities for Non-English Datasets in the Dataset Viewer

By

•

Jul 10

• 4

Article

MInference 1.0: 10x Faster Million Context Inference with a Single GPU

By

•

Jul 11

• 10

Article

RegMix: Data Mixture as Regression for Language Model Pre-training

By

•

Jul 11

• 8

Article

Train a Llama model from scratch

By

•

26 days ago

• 37

Article

MMLU-Pro-NoMath

By

•

Jul 11

• 3

Adam Molnar

AI & ML interests

Organizations

lunarflu's activity

Perspectives for first principles prompt engineering

dstack: Your LLM Launchpad - From Fine-Tuning to Serving, Simplified

How to communicate in a Pull Request?

Using Writer Framework with Hugging Face Spaces

What are Embeddings and Vector Databases?

Extractive Question Answering with AutoTrain

How to get GPT to talk like a consultant

Web Scraping 102

Self-Hosting LLaMA 3.1 70B (or any ~70B LLM) Affordably

Tensor Parallelism

Web Scraping 101

Llama-3.1-Storm-8B: Improved SLM with Self-Curation + Model Merging

∞🧙🏼‍♂️AnyClassifier - Generating Synthetic Data For Text Classification

Data Formats 101

Processing Parquets 101

Outperforming Claude 3.5 Sonnet with Phi-3-mini-4k for graph entity relationship extraction tasks

I Trained a 2D Game Animation Generation Model to Create Complex, Cool Game Actions (Fully Open-Source)

BERT for Bias Detection in Text

The Workflow of PEFT

Context Parallelism

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

2024 Security Feature Highlights

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

The case for specialized pre-training: ultra-fast foundation models for dedicated tasks

Agentic Task Delegation - Making Agents whole again

ArabicWeb24: Creating a High Quality Arabic Web-only Pre-training Dataset

Batch size 30 AdamW vs Batch Size 1 Adafactor SDXL Training Comparison

Unlocking Creativity with Text-to-Image Generation: Exploring LoRA Models and Styles

Google releases Gemma 2 2B, ShieldGemma and Gemma Scope

Introducing TextImage Augmentation for Document Images

SmolLM - blazingly fast and remarkably powerful

Introducing IDEFICS: An Open Reproduction of State-of-the-art Visual Language Model

Fine-tune Llama 3.1 Ultra-Efficiently with Unsloth

Build static HTML spaces

🔥 Argilla 2.0: the data-centric tool for AI makers 🤗

Serverless Inference with Hugging Face and NVIDIA NIMs

LAVE: Zero-shot VQA Evaluation on Docmatix with LLMs - Do We Still Need Fine-Tuning?

ZebraLogic: Benchmarking the Logical Reasoning Ability of Language Models

Are We Ready for Multi-Image Reasoning? Launching VHs: The Visual Haystacks Benchmark!

Announcing BigCodeBench-Hard, and More

Clarity AI Upscaler Reproduction

Finetuning PaliGemma with AutoTrain

Abliterating Refusal and Code LLMs

Llama 3.1 - 405B, 70B & 8B with multilinguality and long context

How NuminaMath Won the 1st AIMO Progress Prize

The Rise of Agentic Data Generation

Taxonomy Completion with Embedding Quantization and an LLM-based Pipeline: A Case Study in Computational Linguistics

Preference Optimization for Vision Language Models

Experimenting with Automatic PII Detection on the Hub using Presidio

Announcing New Hugging Face and Keras NLP integration

How we leveraged distilabel to create an Argilla 2.0 Chatbot

Enhancing Search Capabilities for Non-English Datasets in the Dataset Viewer

MInference 1.0: 10x Faster Million Context Inference with a Single GPU

RegMix: Data Mixture as Regression for Language Model Pre-training

Train a Llama model from scratch

MMLU-Pro-NoMath