Sevde's picture

Sevde

sevdekutuk

·

AI & ML interests

None yet

Recent Activity

upvoted an article 18 days ago

Fine-Tune Whisper For Multilingual ASR with 🤗 Transformers

upvoted an article 19 days ago

Keep the Tokens Flowing: Lessons from 16 Open-Source RL Libraries

liked a model 22 days ago

netflix/void-model

View all activity

Organizations

None yet

upvoted an article 18 days ago

Article

Fine-Tune Whisper For Multilingual ASR with 🤗 Transformers

Nov 3, 2022

•

368

upvoted an article 19 days ago

Article

Keep the Tokens Flowing: Lessons from 16 Open-Source RL Libraries

+7

Mar 10

•

133

upvoted an article 22 days ago

Article

Welcome Gemma 4: Frontier multimodal intelligence on device

+5

23 days ago

•

877

upvoted a paper 25 days ago

EdgeCrafter: Compact ViTs for Edge Dense Prediction via Task-Specialized Distillation

Paper • 2603.18739 • Published Mar 19 • 11

upvoted a collection 25 days ago

Audio Spaces

177 items • Updated 17 days ago • 24

upvoted a paper 29 days ago

DA-Flow: Degradation-Aware Optical Flow Estimation with Diffusion Models

Paper • 2603.23499 • Published Mar 24 • 51

upvoted an article about 1 month ago

Article

LoRA Fine-Tuning BitNet b1.58 LLMs on Heterogeneous Edge GPUs via QVAC Fabric

Mar 17

•

17

upvoted 3 papers about 1 month ago

Attention Residuals

Paper • 2603.15031 • Published Mar 16 • 183

Mixture-of-Depths Attention

Paper • 2603.15619 • Published Mar 16 • 80

TERMINATOR: Learning Optimal Exit Points for Early Stopping in Chain-of-Thought Reasoning

Paper • 2603.12529 • Published Mar 13 • 19

upvoted 2 collections about 1 month ago

SigLino: Vision Foundation Models (SigLIP2 + DINOv3)

Vision encoders distilled from DINOv3 and SigLIP2 (MoE & Dense). CVPR 2026. • 6 items • Updated 14 days ago • 17

Olmo Hybrid

6 items • Updated Mar 5 • 25

upvoted an article about 2 months ago

Article

We Got Claude to Fine-Tune an Open Source LLM

Dec 4, 2025

•

623

upvoted a paper about 2 months ago

LLaVE: Large Language and Vision Embedding Models with Hardness-Weighted Contrastive Learning

Paper • 2503.04812 • Published Mar 4, 2025 • 17

upvoted 2 articles 2 months ago

Article

How to Use Multiple GPUs in Hugging Face Transformers: Device Map vs Tensor Parallelism

Feb 12

•

20

Article

Forge: Scalable Agent RL Framework and Algorithm

Feb 13

•

147

upvoted a paper 2 months ago

jina-embeddings-v5-text: Task-Targeted Embedding Distillation

Paper • 2602.15547 • Published Feb 17 • 26

upvoted a collection 2 months ago

jina-embeddings-v5-text

Our 5th-gen embeddings: two lightweight multilingual models with SOTA performance in retrieval, matching, clustering, and classification. • 29 items • Updated Feb 27 • 38

upvoted 2 articles 2 months ago

Article

Simplifying Alignment: From RLHF to Direct Preference Optimization (DPO)

Jan 19, 2025

•

48

Article

Fine-Tuning Your First Large Language Model (LLM) with PyTorch and Hugging Face

Feb 11, 2025

•

119