Hugging Face - Author | TheMorningPulse.fyi

CONNECT WITH US

AI & Deeptech

How to Use NVIDIA Warp and MjWarp to Accelerate Robotics Simulation and Learning Workflows

By Hugging Face

AI & Deeptech

Know Who Spoke When: Build Real-Time, Multi-Speaker AI with NVIDIA Nemotron 3 Diarization

By Hugging Face

AI & Deeptech

Jun Kim, oMLX creator and maintainer, joins Hugging Face to support the MLX community

By Hugging Face

AI & Deeptech

Transformers now runs llama.cpp quants

By Hugging Face

AI & Deeptech

How UK AISI and EvalEval Are Making Benchmark Results Reproducible

By Hugging Face

AI & Deeptech

Pruning LLMs Like a Physicist: Block Removal as an Ising Optimization Problem

By Hugging Face

AI & Deeptech

tokenizers v1: encode, decode and scaling, measured

By Hugging Face

AI & Deeptech

Your Agent Aced the Task. Will It Do It Again?

By Hugging Face

AI & Deeptech

Rebuilding AUTOMATIC1111 with Gradio Workflow

By Hugging Face

AI & Deeptech

Async GRPO with LoRA across HF Jobs: a bucket, a proxy, and no NCCL

By Hugging Face

AI & Deeptech

NeoMME: an efficient Multimodal-native and Multilingual Encoder

By Hugging Face

AI & Deeptech

Training a coding model to paint watercolours with TRL and OpenEnv

By Hugging Face

AI & Deeptech

Give Your Coding Agents a Memory You Own

By Hugging Face

AI & Deeptech

Fine-tuning a 350M Model for Better Structured Outputs in 100 GRPO Steps

By Hugging Face

AI & Deeptech

BenchMIRT: What are LLM benchmarks actually measuring?

By Hugging Face

AI & Deeptech

Introducing @huggingface/kernels: 200+ WebGPU Kernels for Local AI

By Hugging Face

AI & Deeptech

The Open ASR Leaderboard Adds Its First Global South Language

By Hugging Face

AI & Deeptech

Training and Finetuning Multi-Vector Embedding Models with Sentence Transformers

By Hugging Face

AI & Deeptech

Granite 4.2 LLMs: How They're Built

By Hugging Face

AI & Deeptech

Quantization-Aware Healing: a compressed, 4-bit model that outperforms its full-precision original

By Hugging Face

Hugging Face - Author | TheMorningPulse.fyi | TheMorningPulse.fyi

How to Use NVIDIA Warp and MjWarp to Accelerate Robotics Simulation and Learning Workflows

**Know Who Spoke When: Build Real-Time, Multi-Speaker AI with NVIDIA Nemotron 3 Diarization**

Jun Kim, oMLX creator and maintainer, joins Hugging Face to support the MLX community

Transformers now runs llama.cpp quants

How UK AISI and EvalEval Are Making Benchmark Results Reproducible

Pruning LLMs Like a Physicist: Block Removal as an Ising Optimization Problem

tokenizers v1: encode, decode and scaling, measured

Your Agent Aced the Task. Will It Do It Again?

Rebuilding AUTOMATIC1111 with Gradio Workflow

Async GRPO with LoRA across HF Jobs: a bucket, a proxy, and no NCCL

NeoMME: an efficient Multimodal-native and Multilingual Encoder

Training a coding model to paint watercolours with TRL and OpenEnv

Give Your Coding Agents a Memory You Own

Fine-tuning a 350M Model for Better Structured Outputs in 100 GRPO Steps

BenchMIRT: What are LLM benchmarks actually measuring?

Introducing @huggingface/kernels: 200+ WebGPU Kernels for Local AI

The Open ASR Leaderboard Adds Its First Global South Language

Training and Finetuning Multi-Vector Embedding Models with Sentence Transformers

Granite 4.2 LLMs: How They're Built

Quantization-Aware Healing: a compressed, 4-bit model that outperforms its full-precision original

Know Who Spoke When: Build Real-Time, Multi-Speaker AI with NVIDIA Nemotron 3 Diarization