raphaelcosta (Raphael Costa)

upvoted an article 4 months ago

Article

SmolLM - blazingly fast and remarkably powerful

Jul 16

• 256

upvoted an article 6 months ago

Article

Let's talk about LLM evaluation

By

•

May 23

• 133

upvoted a collection 6 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

upvoted 2 articles 6 months ago

Article

Speculative Decoding for 2x Faster Whisper Inference

Dec 20, 2023

• 15

Article

Bringing the Artificial Analysis LLM Performance Leaderboard to Hugging Face

May 3

• 13

upvoted a paper 6 months ago

An Embarrassingly Simple Approach for LLM with Strong ASR Capacity

Paper • 2402.08846 • Published Feb 13 • 1

upvoted a paper 7 months ago

Introducing Bode: A Fine-Tuned Large Language Model for Portuguese Prompt-Based Task

Paper • 2401.02909 • Published Jan 5 • 2

upvoted an article 7 months ago

Article

Fine-tuning XLS-R for Multi-Lingual ASR with 🤗 Transformers

Nov 15, 2021

• 17

upvoted 3 collections 7 months ago

upvoted 2 papers 7 months ago

LLM Agent Operating System

Paper • 2403.16971 • Published Mar 25 • 65

Improving Language Model-Based Zero-Shot Text-to-Speech Synthesis with Multi-Scale Acoustic Prompts

Paper • 2309.11977 • Published Sep 21, 2023 • 2

upvoted a collection 7 months ago

WhisperKit

Collection

Models, datasets and evaluation results for WhisperKit: https://github.com/argmaxinc/WhisperKit • 4 items • Updated Sep 5 • 6

upvoted a collection 8 months ago

Playground v2.5

Collection

2 items • Updated Feb 27 • 23

upvoted a paper about 1 year ago

AgentTuning: Enabling Generalized Agent Abilities for LLMs

Paper • 2310.12823 • Published Oct 19, 2023 • 35

Raphael Costa PRO

AI & ML interests

Organizations

raphaelcosta's activity

SmolLM - blazingly fast and remarkably powerful

Let's talk about LLM evaluation

Idefics2 🐶

Speculative Decoding for 2x Faster Whisper Inference

Bringing the Artificial Analysis LLM Performance Leaderboard to Hugging Face

An Embarrassingly Simple Approach for LLM with Strong ASR Capacity

Introducing Bode: A Fine-Tuned Large Language Model for Portuguese Prompt-Based Task

Fine-tuning XLS-R for Multi-Lingual ASR with 🤗 Transformers

gazelle v0.2

Llama 3

Medical Evaluation Datasets

LLM Agent Operating System

Improving Language Model-Based Zero-Shot Text-to-Speech Synthesis with Multi-Scale Acoustic Prompts

WhisperKit

Playground v2.5

AgentTuning: Enabling Generalized Agent Abilities for LLMs