gabrielmbmb (Gabriel Martín Blázquez)

upvoted a paper 2 days ago

Self-play with Execution Feedback: Improving Instruction-following Capabilities of Large Language Models

Paper • 2406.13542 • Published 4 days ago • 11

upvoted 2 articles 2 days ago

Article

Data Is Better Together: A Look Back and Forward

4 days ago

• 9

Article

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

By

•

3 days ago

• 8

upvoted a paper 2 days ago

Instruction Pre-Training: Language Models are Supervised Multitask Learners

Paper • 2406.14491 • Published 3 days ago • 45

upvoted a collection 5 days ago

Florence

Collection

9 items • Updated 9 days ago • 121

upvoted 2 collections 9 days ago

Tulu V2.5 Suite

Collection

A suite of models trained using DPO and PPO across a wide variety (up to 14) of preference datasets. See https://arxiv.org/abs/2406.09279 for more! • 41 items • Updated 10 days ago • 8

Nemotron 4 340B

Collection

Nemotron-4: open models for Synthetic Data Generation (SDG). Includes Base, Instruct, and Reward models. • 4 items • Updated 9 days ago • 141

upvoted a paper 10 days ago

Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing

Paper • 2406.08464 • Published 11 days ago • 43

upvoted an article 11 days ago

Article

Putting RL back in RLHF

12 days ago

• 42

upvoted a collection 11 days ago

Stable Diffusion 3

Collection

Stable Diffusion 3 and related models for text-to-image and image-to-image • 2 items • Updated 11 days ago • 64

upvoted a collection 14 days ago

Qwen2

Collection

Qwen2 language models, including pretrained and instruction-tuned models of 5 sizes, including 0.5B, 1.5B, 7B, 57B-A14B, and 72B. • 29 items • Updated 17 days ago • 198

upvoted a paper 15 days ago

Show, Don't Tell: Aligning Language Models with Demonstrated Feedback

Paper • 2406.00888 • Published 21 days ago • 28

upvoted a collection 15 days ago

MiniCPM-2B

Collection

The MiniCPM family of LLMs and VLLMs. • 19 items • Updated 9 days ago • 16

upvoted an article 23 days ago

Article

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

By

•

20 days ago

• 20

upvoted a paper about 1 month ago

LoRA Learns Less and Forgets Less

Paper • 2405.09673 • Published May 15 • 78

upvoted 2 articles about 2 months ago

Article

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

By

•

May 7

• 7

Article

🧑‍⚖️ "Replacing Judges with Juries" using distilabel

By

•

May 3

• 15

upvoted a paper about 2 months ago

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

Paper • 2404.18796 • Published Apr 29 • 67

upvoted an article about 2 months ago

Article

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

By

•

Apr 29

• 27

upvoted a paper about 2 months ago

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

Paper • 2404.03715 • Published Apr 4 • 58

upvoted an article about 2 months ago

Article

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

By

•

19 days ago

• 63

upvoted a paper about 2 months ago

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

Paper • 2309.10400 • Published Sep 19, 2023 • 23

upvoted a paper 2 months ago

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

Paper • 2404.14219 • Published Apr 22 • 239

upvoted a collection 2 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 • 85

upvoted a paper 2 months ago

Silkie: Preference Distillation for Large Visual Language Models

Paper • 2312.10665 • Published Dec 17, 2023 • 10

upvoted 2 papers 3 months ago

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

Paper • 2404.02258 • Published Apr 2 • 102

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

Paper • 2212.05055 • Published Dec 9, 2022 • 5

upvoted a collection 3 months ago

Qwen1.5

Collection

Qwen1.5 is the improved version of Qwen, the large language model series developed by Alibaba Cloud. • 55 items • Updated 18 days ago • 195

upvoted 2 papers 3 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 • 32

upvoted a collection 3 months ago

boulderspot

Collection

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

upvoted a paper 3 months ago

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

Paper • 2403.03507 • Published Mar 6 • 179

upvoted a paper 4 months ago

Yi: Open Foundation Models by 01.AI

Paper • 2403.04652 • Published Mar 7 • 59

upvoted a paper 5 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

Collection

44 items • Updated 11 days ago • 126

upvoted 3 collections 7 months ago

upvoted a collection 8 months ago

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 Apr 12 • 141

Gabriel Martín Blázquez

AI & ML interests

Organizations

gabrielmbmb's activity

Data Is Better Together: A Look Back and Forward

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

Putting RL back in RLHF

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

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

🧑‍⚖️ "Replacing Judges with Juries" using distilabel

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

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