Markus's picture

In a Training Loop 🔄

Markus PRO

marksverdhei

NbAiLab

·

marksverdhei

AI & ML interests

NLP

Recent Activity

liked a model about 3 hours ago

Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign

liked a model about 3 hours ago

nvidia/nemotron-speech-streaming-en-0.6b

liked a model about 8 hours ago

Qwen/Qwen3-TTS-12Hz-0.6B-Base

View all activity

Organizations

upvoted a collection about 8 hours ago

Qwen3-TTS

7 items • Updated 4 days ago • 222

upvoted a changelog 4 days ago

Changelog

Sort Models by Parameter Size

4 days ago

• 18

upvoted 2 changelogs 6 days ago

Changelog

Set your primary organization on your profile

Dec 19, 2025

• 106

Changelog

HuggingChat for Papers

19 days ago

• 97

upvoted a collection 6 days ago

FP8 quants

A collection of my FP8 quants for models missing this. • 2 items • Updated 6 days ago • 1

upvoted an article 7 days ago

Article

New in llama.cpp: Anthropic Messages API

7 days ago

•

32

upvoted a collection 24 days ago

Janus

Janus is a novel autoregressive framework that unifies multimodal understanding and generation. • 8 items • Updated Nov 27, 2025 • 21

upvoted 2 collections about 1 month ago

Co-PatcheR

Co-PatcheR: Collaborative Software Patching with Component(s)-specific Small Reasoning Models • 3 items • Updated May 29, 2025 • 1

VulnLLM-R

Data and model for VulnLLM-R: Specialized Reasoning LLM with Agent Scaffold for Vulnerability Detection • 9 items • Updated Dec 17, 2025 • 8

upvoted an article about 1 month ago

Article

We Got Claude to Fine-Tune an Open Source LLM

Dec 4, 2025

•

582

upvoted an article about 2 months ago

Article

New in llama.cpp: Model Management

Dec 11, 2025

•

115

upvoted a collection about 2 months ago

Definition modeling

Models to generate contextualized word definitions • 22 items • Updated Nov 4, 2025 • 1

upvoted a changelog about 2 months ago

Changelog

Duplicate Datasets

Dec 3, 2025

• 102

upvoted 2 collections about 2 months ago

Ministral 3

A collection of edge models, with Base, Instruct and Reasoning variants, in 3 different sizes: 3B, 8B and 14B. All with vision capabilities. • 9 items • Updated Dec 2, 2025 • 149

Mistral Large 3

A state-of-the-art, open-weight, general-purpose multimodal model with a granular Mixture-of-Experts architecture. • 4 items • Updated Dec 2, 2025 • 85

upvoted a paper 2 months ago

Tiny Model, Big Logic: Diversity-Driven Optimization Elicits Large-Model Reasoning Ability in VibeThinker-1.5B

Paper • 2511.06221 • Published Nov 9, 2025 • 133

upvoted a collection 3 months ago

Cerebras REAP

Sparse MoE models compressed using REAP (Router-weighted Expert Activation Pruning) method • 24 items • Updated 4 days ago • 92

upvoted an article 3 months ago

Article

Sentence Transformers is joining Hugging Face!

Oct 22, 2025

•

87

upvoted a changelog 4 months ago

Changelog

GGUF Metadata Editor

Oct 7, 2025

• 81

upvoted a paper 4 months ago

Reinforcement Learning on Pre-Training Data

Paper • 2509.19249 • Published Sep 23, 2025 • 67