Gabriel Martín Blázquez's picture

Gabriel Martín Blázquez

gabrielmbmb

·

https://gabrielmb.com

AI & ML interests

ML Engineer

Organizations

gabrielmbmb's activity

upvoted an article 1 day ago

Article

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

By

•

3 days ago

• 20

upvoted a paper 14 days ago

LoRA Learns Less and Forgets Less

Paper • 2405.09673 • Published 17 days ago • 73

upvoted an article 25 days ago

Article

Can we create pedagogically valuable multi-turn synthetic datasets from Cosmopedia?

By

•

25 days ago

• 6

upvoted an article 29 days ago

Article

🧑‍⚖️ "Replacing Judges with Juries" using distilabel

By

•

29 days ago

• 14

upvoted a paper about 1 month ago

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

Paper • 2404.18796 • Published Apr 29 • 63

upvoted an article about 1 month ago

Article

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

By

•

Apr 29

• 27

upvoted a paper about 1 month ago

Direct Nash Optimization: Teaching Language Models to Self-Improve with General Preferences

Paper • 2404.03715 • Published Apr 4 • 58

upvoted an article about 1 month ago

Article

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

By

•

Apr 26

• 55

upvoted 2 papers about 1 month ago

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

Paper • 2309.10400 • Published Sep 19, 2023 • 22

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

Paper • 2404.14219 • Published Apr 22 • 238

upvoted a collection about 2 months ago

Idefics2 🐶

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 26 days ago • 83

upvoted 2 papers about 2 months ago

Silkie: Preference Distillation for Large Visual Language Models

Paper • 2312.10665 • Published Dec 17, 2023 • 10

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

Paper • 2404.02258 • Published Apr 2 • 102

upvoted a paper 2 months ago

Sparse Upcycling: Training Mixture-of-Experts from Dense Checkpoints

Paper • 2212.05055 • Published Dec 9, 2022 • 5

upvoted a collection 2 months ago

Qwen1.5

Qwen1.5 is the improved version of Qwen, the large language model series developed by Alibaba Cloud. • 55 items • Updated 20 days ago • 183

upvoted 2 papers 2 months ago

Jamba: A Hybrid Transformer-Mamba Language Model

Paper • 2403.19887 • Published Mar 28 • 99

sDPO: Don't Use Your Data All at Once

Paper • 2403.19270 • Published Mar 28 • 31

upvoted a collection 2 months ago

boulderspot

find places to climb outside from aerial imagery • 4 items • Updated Apr 1 • 3

upvoted 2 papers 3 months ago

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

Paper • 2403.03507 • Published Mar 6 • 176

Yi: Open Foundation Models by 01.AI

Paper • 2403.04652 • Published Mar 7 • 59

upvoted a paper 4 months ago

Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads

Paper • 2401.10774 • Published Jan 19 • 50

upvoted a collection 5 months ago

MoEs papers reading list

43 items • Updated 3 days ago • 123

upvoted 2 collections 6 months ago

Notus 7B v1

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

Recent models: last 100 repos, sorted by creation date

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 • 447

upvoted 2 collections 7 months ago

Handbook v0.1 models and datasets

Models and datasets for v0.1 of the alignment handbook • 6 items • Updated Nov 10, 2023 • 23

Zephyr 7B

Models, datasets, and demos associated with Zephyr 7B. For code to train the models, see: https://github.com/huggingface/alignment-handbook • 9 items • Updated Apr 12 • 138