mathiasn1 (Mathias Nielsen)

upvoted a collection 12 days ago

💻 Local SmolLMs

SmolLM models in MLC, ONNX and GGUF format for local applications + in-browser demos • 14 items • Updated 10 days ago • 38

upvoted a collection 22 days ago

🕹️ AI Games

Collection

An ongoing collection of games you can play on HF Spaces • 14 items • Updated Jun 20 • 23

upvoted a collection 30 days ago

Gemma 2 2B Release

Collection

The 2.6B parameter version of Gemma 2. • 6 items • Updated 30 days ago • 73

upvoted 2 collections about 1 month ago

Llama 3.1

Collection

This collection hosts the transformers and original repos of the Meta Llama 3.1, Llama Guard 3 and Prompt Guard models • 11 items • Updated 28 days ago • 525

DCLM

Collection

DCLM Models + Datasets • 7 items • Updated Jul 22 • 38

upvoted a paper 2 months ago

DETRs Beat YOLOs on Real-time Object Detection

Paper • 2304.08069 • Published Apr 17, 2023 • 11

upvoted an article 2 months ago

Article

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

Jun 24

• 162

upvoted a paper 2 months ago

Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks

Paper • 2311.06242 • Published Nov 10, 2023 • 77

upvoted 3 collections 2 months ago

upvoted 5 collections 4 months ago

LlamaForTokenClassification

Collection

Fine Tuned llama variants for Token Classification • 6 items • Updated 22 days ago • 2

PaliGemma Release

Collection

Pretrained and mix checkpoints for PaliGemma • 16 items • Updated 30 days ago • 133

T5 release

Collection

The original T5 transformer release was done in two steps, the original T5 checkpoints and the improved T5v1 • 9 items • Updated 30 days ago • 11

Flan-T5 release

Collection

The Flan-T5 covers 4 checkpoints of different sizes each time. It also includes upgrades versions trained using Universal sampling • 7 items • Updated 30 days ago • 18

BERT release

Collection

Regroups the original BERT models released by the Google team. Except for the models marked otherwise, the checkpoints support English. • 8 items • Updated 30 days ago • 18

upvoted 2 articles 4 months ago

Article

License to Call: Introducing Transformers Agents 2.0

May 13

• 107

Article

Mergoo: Efficiently Build Your Own MoE LLM

By

•

Jun 3

• 39

upvoted a collection 4 months ago

NB-Whisper-verbatim

Collection

NB-Whisper models that are mostly suited for linguists and researchers. The output is lowercase and without punctation. • 5 items • Updated Feb 13 • 2

upvoted an article 4 months ago

Article

Powerful ASR + diarization + speculative decoding with Hugging Face Inference Endpoints

May 1

• 60

upvoted 3 papers 4 months ago

KAN: Kolmogorov-Arnold Networks

Paper • 2404.19756 • Published Apr 30 • 108

LoRA Land: 310 Fine-tuned LLMs that Rival GPT-4, A Technical Report

Paper • 2405.00732 • Published Apr 29 • 118

Better & Faster Large Language Models via Multi-token Prediction

Paper • 2404.19737 • Published Apr 30 • 73

upvoted 3 articles 4 months ago

Article

⚗️ 🧑🏼‍🌾 Let's grow some Domain Specific Datasets together

By

•

Apr 29

• 28

Article

🦙⚗️ Using Llama3 and distilabel to build fine-tuning datasets

By

•

Jun 4

• 66

Article

Post-OCR-Correction: 1 billion words dataset of automated OCR correction by LLM

By

•

Apr 26

• 13

upvoted a paper 4 months ago

PoSE: Efficient Context Window Extension of LLMs via Positional Skip-wise Training

Paper • 2309.10400 • Published Sep 19, 2023 • 25

upvoted 2 collections 4 months ago

OpenELM Instruct Models

Collection

4 items • Updated Jun 19 • 113

OpenELM Pretrained Models

Collection

4 items • Updated Jun 19 • 46

upvoted a paper 4 months ago

OpenELM: An Efficient Language Model Family with Open-source Training and Inference Framework

Paper • 2404.14619 • Published Apr 22 • 124

upvoted a collection 4 months ago

Phi-3

Collection

Phi-3 family of small language and multi-modal models. Language models are available in short- and long-context lengths. • 26 items • Updated 10 days ago • 442

upvoted an article 4 months ago

Article

Introducing the Open Chain of Thought Leaderboard

Apr 23

• 23

upvoted a paper 4 months ago

Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone

Paper • 2404.14219 • Published Apr 22 • 247

upvoted 2 collections 4 months ago

Llama 2 Family

Collection

This collection hosts the transformers and original repos of the Llama 2 and Llama Guard releases • 13 items • Updated 28 days ago • 60

Meta Llama 3

Collection

This collection hosts the transformers and original repos of the Meta Llama 3 and Llama Guard 2 releases • 5 items • Updated 28 days ago • 668

upvoted an article 4 months ago

Article

Introducing the LiveCodeBench Leaderboard - Holistic and Contamination-Free Evaluation of Code LLMs

Apr 16

• 12

upvoted a collection 4 months ago

Dinov2

Collection

5 items • Updated Jan 16 • 9

upvoted 2 collections 5 months ago

Idefics2 🐶

Collection

Idefics2-8B is a foundation vision-language model. In this collection, you will find the models, datasets and demo related to its creation. • 11 items • Updated May 6 • 88

distil-large-v3

Collection

This collection contains the model repositories for distil-large-v3, which provides support for the most popular Whisper libraries. • 4 items • Updated Mar 21 • 5

upvoted a paper 5 months ago

Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention

Paper • 2404.07143 • Published Apr 10 • 103

upvoted 2 collections 5 months ago

C4AI Command R

Collection

C4AI Command-R is a research release of a 35 billion parameter highly performant generative model. Command-R is a large language model with open weigh • 4 items • Updated about 3 hours ago • 14

Papers We've Read

Collection

Papers discussed in the H4 journal club • 3 items • Updated Apr 12 • 8

upvoted a paper 5 months ago

ORPO: Monolithic Preference Optimization without Reference Model

Paper • 2403.07691 • Published Mar 12 • 59

upvoted 2 collections 5 months ago

Zephyr ORPO

Collection

Models and datasets to align LLMs with Odds Ratio Preference Optimisation (ORPO). Recipes here: https://github.com/huggingface/alignment-handbook • 3 items • Updated Apr 12 • 16

DBRX

Collection

DBRX is a mixture-of-experts (MoE) large language model trained from scratch by Databricks. • 3 items • Updated Mar 27 • 90

upvoted 2 papers 5 months ago

One-Step Image Translation with Text-to-Image Models

Paper • 2403.12036 • Published Mar 18 • 7

Fast High-Resolution Image Synthesis with Latent Adversarial Diffusion Distillation

Paper • 2403.12015 • Published Mar 18 • 63

upvoted 2 collections 6 months ago

Danish Benchmarks

Collection

Benchmarks for evaluating Danish Models. • 2 items • Updated Jun 9 • 3

State-of-the-art Danish Models

Collection

These models constitute state-of-the-art models for Danish within their respective domain (highlighted below the model). • 13 items • Updated Apr 11 • 9

upvoted 2 papers 6 months ago

Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Paper • 2403.05530 • Published Mar 8 • 59

Personalized Audiobook Recommendations at Spotify Through Graph Neural Networks

Paper • 2403.05185 • Published Mar 8 • 20

upvoted 2 collections 6 months ago

Llama2 HQQ Quantized Models

Collection

LLama2 models quantized using https://github.com/mobiusml/hqq • 6 items • Updated Mar 29 • 5

Mixtral HQQ Quantized Models

Collection

4-bit and 2-bit Mixtral models quantized using https://github.com/mobiusml/hqq • 9 items • Updated Mar 29 • 14

upvoted 2 papers 6 months ago

GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection

Paper • 2403.03507 • Published Mar 6 • 182

Unifying Vision, Text, and Layout for Universal Document Processing

Paper • 2212.02623 • Published Dec 5, 2022 • 10

upvoted a collection 6 months ago

Zephyr 7B Gemma

Collection

Models, dataset, and Demo for Zephyr 7B Gemma. For code to train the models, see: https://github.com/huggingface/alignment-handbook • 5 items • Updated Apr 12 • 15

upvoted 3 papers 6 months ago

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

Paper • 2402.17764 • Published Feb 27 • 589

Synthetic Data (Almost) from Scratch: Generalized Instruction Tuning for Language Models

Paper • 2402.13064 • Published Feb 20 • 46

LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens

Paper • 2402.13753 • Published Feb 21 • 110

upvoted a collection 6 months ago

🌌 Cosmopedia

Collection

Resources for Cosmopedia dataset • 6 items • Updated 12 days ago • 8

Mathias Nielsen

AI & ML interests

Organizations

mathiasn1's activity

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

License to Call: Introducing Transformers Agents 2.0

Mergoo: Efficiently Build Your Own MoE LLM

Powerful ASR + diarization + speculative decoding with Hugging Face Inference Endpoints

⚗️ 🧑🏼‍🌾 Let's grow some Domain Specific Datasets together

🦙⚗️ Using Llama3 and distilabel to build fine-tuning datasets

Post-OCR-Correction: 1 billion words dataset of automated OCR correction by LLM

Introducing the Open Chain of Thought Leaderboard

Introducing the LiveCodeBench Leaderboard - Holistic and Contamination-Free Evaluation of Code LLMs