💼 Hiring

Luigi

Luigi

·

AI & ML interests

NLP / ASR / Chat LLM / VLMs

Recent Activity

updated a model about 1 hour ago

Luigi/gemma-4-E2B-meeting-agent-zh-GGUF

published a model about 1 hour ago

Luigi/gemma-4-E2B-meeting-agent-zh-GGUF

liked a model 1 day ago

ornith-ai/Ornith-1.5-9B-DFlash

View all activity

Organizations

upvoted a paper 27 days ago

Step-Audio 2 Technical Report

Paper • 2507.16632 • Published Jul 22, 2025 • 77

upvoted 2 collections 2 months ago

ASR

Automatic Speech Recognition Models • 5 items • Updated Jul 26 • 6

LiteRT

LiteRT (.tflite) bundles for soniqo.audio. ASR, VAD, diarization, speaker ID, streaming, TTS — served by speech-cloud and speech-core. • 17 items • Updated 8 days ago • 2

upvoted a collection 6 months ago

Streaming TTS

Streaming text-to-speech models and frameworks • 3 items • Updated Apr 11 • 1

upvoted a collection 9 months ago

Falcon-H1-Tiny

A series of extremely small, yet powerful language models redefining capabilities at small scale • 19 items • Updated Aug 13 • 38

upvoted a paper 12 months ago

In-the-Flow Agentic System Optimization for Effective Planning and Tool Use

Paper • 2510.05592 • Published Oct 7, 2025 • 113

upvoted a paper about 1 year ago

Why Language Models Hallucinate

Paper • 2509.04664 • Published Sep 4, 2025 • 200

upvoted an article about 1 year ago

Article

Welcome EmbeddingGemma, Google's new efficient embedding model

+4

tomaarsen, Xenova, alvarobartt, ariG23498, pcuenq, sergiopaniego

•

Sep 4, 2025

• 280

upvoted a changelog about 1 year ago

Hugging Face Changelog

Introducing HF Jobs: Run scalable compute jobs on Hugging Face

Jul 30, 2025

• 206

upvoted 6 papers about 1 year ago

InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency

Paper • 2508.18265 • Published Aug 25, 2025 • 222

FastVLM: Efficient Vision Encoding for Vision Language Models

Paper • 2412.13303 • Published Dec 17, 2024 • 77

MobileCLIP2: Improving Multi-Modal Reinforced Training

Paper • 2508.20691 • Published Aug 28, 2025 • 9

LoRA: Low-Rank Adaptation of Large Language Models

Paper • 2106.09685 • Published Jun 17, 2021 • 66

QLoRA: Efficient Finetuning of Quantized LLMs

Paper • 2305.14314 • Published May 23, 2023 • 64

MiniRAG: Towards Extremely Simple Retrieval-Augmented Generation

Paper • 2501.06713 • Published Jan 12, 2025 • 4

upvoted 4 articles over 1 year ago

Article

Deriving DPO's Loss

hba123

•

Dec 24, 2024

• 30

Article

Preference Tuning LLMs with Direct Preference Optimization Methods

+3

kashif, edbeeching, lewtun, lvwerra, osanseviero

•

Jan 18, 2024

• 85

Article

Fine-tuning SmolLM with Group Relative Policy Optimization (GRPO) by following the Methodologies

prithivMLmods

•

Feb 17, 2025

• 30

Article

Proximal Policy Optimization (PPO)

ThomasSimonini

•

Aug 5, 2022

• 95

upvoted a collection over 1 year ago

high-quality Chinese training datasets

a suite of high-quality Chinese datasets, used for pretraining, fine-tuning or preference alignment. And the models trained on these datasets. • 13 items • Updated May 22, 2025 • 24