Santiago Garcia's picture

Santiago Garcia

santyzenith

·

santyzenith

AI & ML interests

Large language models, Natural Language Processing, Computer Vision, Spanish Large language models.

Organizations

santyzenith's activity

upvoted a paper 3 days ago

DataComp-LM: In search of the next generation of training sets for language models

Paper • 2406.11794 • Published Jun 17 • 44

upvoted an article 5 days ago

Article

SmolLM - blazingly fast and remarkably powerful

6 days ago

• 149

upvoted an article 17 days ago

Article

From PyTorch DDP to 🤗 Accelerate to 🤗 Trainer, mastery of distributed training with ease

Oct 21, 2022

• 7

upvoted a paper 18 days ago

Tuna: Instruction Tuning using Feedback from Large Language Models

Paper • 2310.13385 • Published Oct 20, 2023 • 9

upvoted a collection 18 days ago

Knowledge distillation

88 items • Updated Feb 7 • 6

upvoted an article 18 days ago

Article

Putting RL back in RLHF

Jun 12

• 55

upvoted an article 19 days ago

Article

Fine-Tune Whisper with 🤗 Transformers

Nov 3, 2022

• 56

upvoted 6 papers 19 days ago

Datasets: A Community Library for Natural Language Processing

Paper • 2109.02846 • Published Sep 7, 2021 • 8

Estimating Knowledge in Large Language Models Without Generating a Single Token

Paper • 2406.12673 • Published Jun 18 • 7

A Systematic Survey of Text Summarization: From Statistical Methods to Large Language Models

Paper • 2406.11289 • Published Jun 17 • 5

Adam-mini: Use Fewer Learning Rates To Gain More

Paper • 2406.16793 • Published 27 days ago • 65

Aligning Teacher with Student Preferences for Tailored Training Data Generation

Paper • 2406.19227 • Published 25 days ago • 23

Direct Preference Knowledge Distillation for Large Language Models

Paper • 2406.19774 • Published 24 days ago • 21

upvoted an article 24 days ago

Article

Illustrating Reinforcement Learning from Human Feedback (RLHF)

Dec 9, 2022

• 58

upvoted 3 collections 25 days ago

Gemma 2 Release

10 items • Updated 25 days ago • 129

Qwen2

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 Jun 6 • 257

Probably DPO datasets

A collection of datasets that probably support DPO • 146 items • Updated 25 days ago • 8

upvoted a collection about 1 month ago

FP8 LLMs for vLLM

Accurate FP8 quantized models by Neural Magic, ready for use with vLLM! • 22 items • Updated about 9 hours ago • 32

upvoted 3 articles about 1 month ago

Article

Training and Finetuning Embedding Models with Sentence Transformers v3

May 28

• 123

Article

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

By

•

Jun 4

• 65

Article

Mergoo: Efficiently Build Your Own MoE LLM

By

•

Jun 3

• 38

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 Jun 6 • 202

upvoted 4 articles 3 months ago

Article

Fine-tune Llama 3 with ORPO

By

•

Apr 22

• 212

Article

Assisted Generation: a new direction toward low-latency text generation

May 11, 2023

• 14

Article

Faster fine-tuning using TRL & Unsloth

Jan 10

• 28

Article

RAG chatbot using llama3

By

•

14 days ago

• 52