Svngoku (NIONGOLO Chrys Fé-Marty)

upvoted an article 18 days ago

Article

Fine-tuning a token classification model for legal data using Argilla and AutoTrain

By

•

22 days ago

• 11

upvoted an article 22 days ago

Article

Fine-Tune Whisper with 🤗 Transformers

Nov 3, 2022

• 87

upvoted an article 26 days ago

Article

Llama 3.1 - 405B, 70B & 8B with multilinguality and long context

Jul 23

• 196

upvoted 3 papers 28 days ago

Law of Vision Representation in MLLMs

Paper • 2408.16357 • Published about 1 month ago • 92

CogVLM2: Visual Language Models for Image and Video Understanding

Paper • 2408.16500 • Published about 1 month ago • 56

AfriMTE and AfriCOMET: Empowering COMET to Embrace Under-resourced African Languages

Paper • 2311.09828 • Published Nov 16, 2023 • 1

upvoted an article 29 days ago

Article

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

By

•

Jun 3

• 26

upvoted 6 papers about 1 month ago

Fine-tuning Large Language Models with Human-inspired Learning Strategies in Medical Question Answering

Paper • 2408.07888 • Published Aug 15 • 10

upvoted an article about 1 month ago

Article

Fine-tune Llama 3.1 Ultra-Efficiently with Unsloth

By

•

Jul 29

• 206

upvoted an article about 2 months ago

Article

Universal Image Segmentation with Mask2Former and OneFormer

Jan 19, 2023

• 7

upvoted a collection about 2 months ago

Llama 3.1

Collection

This collection hosts the transformers and original repos of the Llama 3.1, Llama Guard 3 and Prompt Guard models • 11 items • Updated 3 days ago • 584

upvoted 4 collections 2 months ago

CogVLM2

Collection

This collection hosts the repos of the THUDM's CogVLM2 releases • 8 items • Updated Aug 18 • 17

InternVL 2.0

Collection

Expanding Performance Boundaries of Open-Source MLLM • 16 items • Updated Aug 10 • 73

H2O Danube3

Collection

6 items • Updated Jul 16 • 52

InternLM2.5

Collection

14 items • Updated 14 days ago • 67

upvoted a paper 3 months ago

RodinHD: High-Fidelity 3D Avatar Generation with Diffusion Models

Paper • 2407.06938 • Published Jul 9 • 21

upvoted a collection 3 months ago

C4AI Aya 23

Collection

Aya 23 is an open weights research release of an instruction fine-tuned model with highly advanced multilingual capabilities. • 4 items • Updated Aug 6 • 45

upvoted 2 papers 3 months ago

AfriQA: Cross-lingual Open-Retrieval Question Answering for African Languages

Paper • 2305.06897 • Published May 11, 2023 • 7

AfroDigits: A Community-Driven Spoken Digit Dataset for African Languages

Paper • 2303.12582 • Published Mar 22, 2023 • 20

upvoted a paper 4 months ago

Masked Audio Generation using a Single Non-Autoregressive Transformer

Paper • 2401.04577 • Published Jan 9 • 41

upvoted 2 articles 4 months ago

Article

Fine-tuning 20B LLMs with RLHF on a 24GB consumer GPU

Mar 9, 2023

• 30

Article

🤗 PEFT: Parameter-Efficient Fine-Tuning of Billion-Scale Models on Low-Resource Hardware

Feb 10, 2023

• 35

upvoted a collection 4 months ago

Seamless Communication

Collection

A significant step towards removing language barriers through expressive, fast and high-quality AI translation. • 16 items • Updated Jan 16 • 144

upvoted a paper 4 months ago

ShareGPT4Video: Improving Video Understanding and Generation with Better Captions

Paper • 2406.04325 • Published Jun 6 • 71

upvoted a collection 4 months ago

IrokoBench

Collection

a human-translated benchmark dataset for 16 African languages covering three tasks: NLI, MMLU and MGSM • 6 items • Updated May 31 • 17

upvoted an article 4 months ago

Article

Faster fine-tuning using TRL & Unsloth

Jan 10

• 35

upvoted an article 5 months ago

Article

Fine-tuning MMS Adapter Models for Multi-Lingual ASR

Jun 19, 2023

• 10

upvoted 4 papers about 1 year ago

MVDream: Multi-view Diffusion for 3D Generation

Paper • 2308.16512 • Published Aug 31, 2023 • 101

FocalFormer3D : Focusing on Hard Instance for 3D Object Detection

Paper • 2308.04556 • Published Aug 8, 2023 • 8

Single-Shot Implicit Morphable Faces with Consistent Texture Parameterization

Paper • 2305.03043 • Published May 4, 2023 • 5

BLOOM: A 176B-Parameter Open-Access Multilingual Language Model

Paper • 2211.05100 • Published Nov 9, 2022 • 28

NIONGOLO Chrys Fé-Marty PRO

AI & ML interests

Organizations

Svngoku's activity

Fine-tuning a token classification model for legal data using Argilla and AutoTrain

Fine-Tune Whisper with 🤗 Transformers

Llama 3.1 - 405B, 70B & 8B with multilinguality and long context

Law of Vision Representation in MLLMs

CogVLM2: Visual Language Models for Image and Video Understanding

AfriMTE and AfriCOMET: Empowering COMET to Embrace Under-resourced African Languages

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

Fine-tuning Large Language Models with Human-inspired Learning Strategies in Medical Question Answering

Automated Design of Agentic Systems

Med42-v2: A Suite of Clinical LLMs

ZePo: Zero-Shot Portrait Stylization with Faster Sampling

Imagen 3

Generative Photomontage

Fine-tune Llama 3.1 Ultra-Efficiently with Unsloth

Universal Image Segmentation with Mask2Former and OneFormer

Llama 3.1

CogVLM2

InternVL 2.0

H2O Danube3

InternLM2.5

RodinHD: High-Fidelity 3D Avatar Generation with Diffusion Models

C4AI Aya 23

AfriQA: Cross-lingual Open-Retrieval Question Answering for African Languages

AfroDigits: A Community-Driven Spoken Digit Dataset for African Languages

Masked Audio Generation using a Single Non-Autoregressive Transformer

Fine-tuning 20B LLMs with RLHF on a 24GB consumer GPU

🤗 PEFT: Parameter-Efficient Fine-Tuning of Billion-Scale Models on Low-Resource Hardware

Seamless Communication

ShareGPT4Video: Improving Video Understanding and Generation with Better Captions

IrokoBench

Faster fine-tuning using TRL & Unsloth

Fine-tuning MMS Adapter Models for Multi-Lingual ASR

MVDream: Multi-view Diffusion for 3D Generation

FocalFormer3D : Focusing on Hard Instance for 3D Object Detection

Single-Shot Implicit Morphable Faces with Consistent Texture Parameterization

BLOOM: A 176B-Parameter Open-Access Multilingual Language Model