75 63 237

Alvaro Bartolome

alvarobartt

https://alvarobartt.github.io/

alvarobartt

AI & ML interests

ml @argilla / open-source and machine learning

Articles

💨 Introducing Notus: a DPO fine-tune of Zephyr with a focus on high-quality data

Dec 1, 2023

🤗 LLM suggestions in Argilla with HuggingFace Inference Endpoints

Sep 20, 2023

Organizations

alvarobartt's activity

upvoted a paper 3 days ago

Prometheus 2: An Open Source Language Model Specialized in Evaluating Other Language Models

Paper • 2405.01535 • Published 4 days ago • 55

upvoted 2 collections 4 days ago

SystemChat Preferences

Collection

This collection contains the results of the effort on extending `abacusai/SystemChat-1.1` to convert it into a preference dataset • 12 items • Updated 6 days ago • 1

Capybara Preferences

Collection

This collection contains the results of the effort on extending `LDJnr/Capybara` to convert it into a preference dataset, with 7B LLMs • 8 items • Updated 19 days ago • 1

upvoted a paper 6 days ago

Replacing Judges with Juries: Evaluating LLM Generations with a Panel of Diverse Models

Paper • 2404.18796 • Published 7 days ago • 56

upvoted a paper 11 days ago

Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data

Paper • 2404.14367 • Published 14 days ago • 1

upvoted an article 12 days ago

Article

Jack of All Trades, Master of Some, a Multi-Purpose Transformer Agent

14 days ago

• 64

upvoted a paper 13 days ago

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

Paper • 2404.14219 • Published 14 days ago • 227

upvoted 4 papers 16 days ago

Is DPO Superior to PPO for LLM Alignment? A Comprehensive Study

Paper • 2404.10719 • Published 20 days ago • 3

Best Practices and Lessons Learned on Synthetic Data for Language Models

Paper • 2404.07503 • Published 25 days ago • 25

Pre-training Small Base LMs with Fewer Tokens

Paper • 2404.08634 • Published 24 days ago • 32

Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length

Paper • 2404.08801 • Published 24 days ago • 59

upvoted an article 17 days ago

Article

Fine-tune Llama 3 with ORPO

•

14 days ago

• 161

upvoted a collection 17 days ago

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 18 days ago • 468

upvoted an article 25 days ago

Article

Making thousands of open LLMs bloom in the Vertex AI Model Garden

26 days ago

• 16

upvoted a collection 25 days 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 24 days ago • 13

upvoted a paper 26 days ago

LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders

Paper • 2404.05961 • Published 27 days ago • 61

upvoted a paper 27 days ago

Mixture-of-Depths: Dynamically allocating compute in transformer-based language models

Paper • 2404.02258 • Published Apr 2 • 98

upvoted an article 27 days ago

Article

Hugging Face and Google partner for open AI collaboration

Jan 25

• 1

upvoted a collection about 1 month ago

Qwen1.5

Collection

Qwen1.5 is the improved version of Qwen, the large language model series developed by Alibaba Cloud. • 55 items • Updated 7 days ago • 158

upvoted a paper about 1 month ago

sDPO: Don't Use Your Data All at Once

Paper • 2403.19270 • Published Mar 28 • 30

upvoted a collection about 1 month ago

Foundation AI Papers

Collection

Curated List of Must-Reads on LLM reasoning at Temus AI team • 134 items • Updated 7 days ago • 22

upvoted a paper about 1 month ago

Long-form factuality in large language models

Paper • 2403.18802 • Published Mar 27 • 23

upvoted 3 collections about 1 month ago

Recent Mamba Papers

Collection

[NB: Notes are from TuringPost] • 3 items • Updated Mar 26 • 9

About ORPO

Collection

Contains some information and experiments fine-tuning LLMs using 🤗 `trl.ORPOTrainer` • 8 items • Updated 3 days ago • 5

ORPO

Collection

This is the official collection of "ORPO: Monolithic Preference Optimization without Reference Model". • 5 items • Updated 24 days ago • 10

upvoted a paper about 1 month ago

ORPO: Monolithic Preference Optimization without Reference Model

Paper • 2403.07691 • Published Mar 12 • 53

upvoted a collection about 2 months ago

Deita

Collection

12 items • Updated Dec 20, 2023 • 7

upvoted a collection 2 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 24 days ago • 15

upvoted 2 papers 2 months ago

StarCoder 2 and The Stack v2: The Next Generation

Paper • 2402.19173 • Published Feb 29 • 120

Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models

Paper • 2402.17177 • Published Feb 27 • 87

upvoted a collection 2 months ago

💫 StarCoder2

Collection

StarCoder2 models and datasets! • 8 items • Updated Mar 1 • 72

upvoted a paper 2 months ago

Multi-LoRA Composition for Image Generation

Paper • 2402.16843 • Published Feb 26 • 28

upvoted a collection 2 months ago

Gemma release

Collection

Groups the Gemma models released by the Google team. • 40 items • Updated 25 days ago • 291

upvoted a collection 3 months ago

OLMo Suite

Collection

Artifacts for the first set of OLMo models. • 12 items • Updated 13 days ago • 34

upvoted 6 papers 4 months ago

Understanding LLMs: A Comprehensive Overview from Training to Inference

Paper • 2401.02038 • Published Jan 4 • 59

TinyLlama: An Open-Source Small Language Model

Paper • 2401.02385 • Published Jan 4 • 80

Mixtral of Experts

Paper • 2401.04088 • Published Jan 8 • 152

LLM in a flash: Efficient Large Language Model Inference with Limited Memory

Paper • 2312.11514 • Published Dec 12, 2023 • 252

Improving Text Embeddings with Large Language Models

Paper • 2401.00368 • Published Dec 31, 2023 • 72

Some things are more CRINGE than others: Preference Optimization with the Pairwise Cringe Loss

Paper • 2312.16682 • Published Dec 27, 2023 • 4

upvoted a collection 4 months ago

Notux 8x7B v1

Collection

Notux 8x7B v1 model (DPO fine-tune of Mixtral 8x7B Instruct v0.1) and datasets used. More information at https://github.com/argilla-io/notus • 6 items • Updated Dec 29, 2023 • 7

upvoted a paper 4 months ago

SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-Scaling

Paper • 2312.15166 • Published Dec 23, 2023 • 55

upvoted 2 collections 4 months ago

Apple MLX-compatible 7B LLMs on the 🤗 Hub

Collection

This collection contains the model weights for 7B LLMs for Apple's MLX framework. Find more information at https://github.com/ml-explore/mlx • 8 items • Updated 3 days ago • 9

Datasets based on UltraFeedback

Collection

This collection contains some datasets created on top of UltraFeedback using Argilla for the dataset exploration and curation, sorted by release date. • 6 items • Updated Mar 19 • 10

upvoted a paper 5 months ago

Prometheus: Inducing Fine-grained Evaluation Capability in Language Models

Paper • 2310.08491 • Published Oct 12, 2023 • 48

upvoted 4 collections 5 months ago

PEFT papers

Collection

A collection of methods that have been implemented in the 🤗 PEFT library • 12 items • Updated Jan 30 • 12

Preference Datasets for DPO

Collection

This collection contains a list of curated preference datasets for DPO fine-tuning for intent alignment of LLMs • 7 items • Updated Apr 4 • 18

Recent models: last 100 repos, sorted by creation date

Collection

The last 100 repos I have created. Sorted by creation date descending, so the most recently created repos appear at the top. • 121 items • Updated Jan 31 • 441

Notus 7B v1

Collection

Notus 7B v1 models (DPO fine-tune of Zephyr SFT) and datasets used. More information at https://github.com/argilla-io/notus • 11 items • Updated Dec 28, 2023 • 17

upvoted a paper 5 months ago

The Falcon Series of Open Language Models

Paper • 2311.16867 • Published Nov 28, 2023 • 11

upvoted a paper 6 months ago

MEGAVERSE: Benchmarking Large Language Models Across Languages, Modalities, Models and Tasks

Paper • 2311.07463 • Published Nov 13, 2023 • 13

upvoted 2 collections 6 months ago

Switch-Transformers release

Collection

This release included various MoE (Mixture of expert) models, based on the T5 architecture . The base models use from 8 to 256 experts. • 9 items • Updated 27 days ago • 11

Custom Components ✨

Collection

Awesome gradio custom components to get you started build your own! • 7 items • Updated Nov 20, 2023 • 31

upvoted 2 papers 6 months ago

Zephyr: Direct Distillation of LM Alignment

Paper • 2310.16944 • Published Oct 25, 2023 • 116

Matryoshka Diffusion Models

Paper • 2310.15111 • Published Oct 23, 2023 • 39

upvoted 2 collections 6 months ago

Core ML Diffusers 🧨

Collection

Some diffusion models ported to Core ML that work with apple/ml-stable-diffusion and huggingface/swift-coreml-diffusers. • 16 items • Updated Sep 7, 2023 • 8

Zephyr 7B

Collection

Models, datasets, and demos associated with Zephyr 7B. For code to train the models, see: https://github.com/huggingface/alignment-handbook • 9 items • Updated 24 days ago • 136

upvoted 3 papers 7 months ago

Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning

Paper • 2205.05638 • Published May 11, 2022 • 3

Emu: Enhancing Image Generation Models Using Photogenic Needles in a Haystack

Paper • 2309.15807 • Published Sep 27, 2023 • 30

Neural Machine Translation of Rare Words with Subword Units

Paper • 1508.07909 • Published Aug 31, 2015 • 4

Alvaro Bartolome

AI & ML interests

Articles

🧑‍⚖️ "Replacing Judges with Juries" using distilabel

Deploying 🤗 Hub models in Vertex AI

🏷️ Build AI Feedback (AIF) datasets for LLM alignment with ⚗️ distilabel

💨 Introducing Notus: a DPO fine-tune of Zephyr with a focus on high-quality data

🤗 LLM suggestions in Argilla with HuggingFace Inference Endpoints

Organizations

alvarobartt's activity

Jack of All Trades, Master of Some, a Multi-Purpose Transformer Agent

Fine-tune Llama 3 with ORPO

Making thousands of open LLMs bloom in the Vertex AI Model Garden

Hugging Face and Google partner for open AI collaboration