Victor Mustar's picture

Victor Mustar PRO

victor

·

victormustar

AI & ML interests

Building the UX of this website

Recent Activity

liked a Space about 1 hour ago

teapotai/teapotchat

liked a model about 1 hour ago

teapotai/teapotllm

reacted to csabakecskemeti's post with 👍 about 2 hours ago

I'm collecting llama-bench results for inference with a llama 3.1 8B q4 and q8 reference models on varoius GPUs. The results are average of 5 executions. The system varies (different motherboard and CPU ... but that probably that has little effect on the inference performance). https://devquasar.com/gpu-gguf-inference-comparison/ the exact models user are in the page I'd welcome results from other GPUs is you have access do anything else you've need in the post. Hopefully this is useful information everyone.

View all activity

Organizations

victor's activity

upvoted a collection about 6 hours ago

UIGEN-T1.5 REASONING MODEL

UIGEN'S Next Iteration. UIGEN-T1.5 is a midway model between 1 and 2, reflecting our new data collection pipeline changes. • 5 items • Updated about 3 hours ago • 4

upvoted a paper 2 days ago

Reinforcement Learning for Reasoning in Small LLMs: What Works and What Doesn't

Paper • 2503.16219 • Published 4 days ago • 38

upvoted a paper 3 days ago

DeepMesh: Auto-Regressive Artist-mesh Creation with Reinforcement Learning

Paper • 2503.15265 • Published 5 days ago • 42

upvoted an article 6 days ago

Article

NVIDIA's GTC 2025 Announcement for Physical AI Developers: New Open Models and Datasets

7 days ago

• 29

upvoted a paper 7 days ago

ReCamMaster: Camera-Controlled Generative Rendering from A Single Video

Paper • 2503.11647 • Published 10 days ago • 117

upvoted 3 papers 12 days ago

YuE: Scaling Open Foundation Models for Long-Form Music Generation

Paper • 2503.08638 • Published 13 days ago • 59

LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL

Paper • 2503.07536 • Published 14 days ago • 80

Crowdsource, Crawl, or Generate? Creating SEA-VL, a Multicultural Vision-Language Dataset for Southeast Asia

Paper • 2503.07920 • Published 14 days ago • 95

upvoted a collection 12 days ago

Gemma 3

All versions of Google's new multimodal models in 1B, 4B, 12B, and 27B sizes. In GGUF, dynamic 4-bit and 16-bit formats. • 29 items • Updated 8 days ago • 43

upvoted an article 12 days ago

Article

Welcome Gemma 3: Google's all new multimodal, multilingual, long context open LLM

13 days ago

• 342

upvoted a collection 12 days ago

Gemma 3 Release

9 items • Updated 11 days ago • 290

upvoted 2 papers 13 days ago

Feature-Level Insights into Artificial Text Detection with Sparse Autoencoders

Paper • 2503.03601 • Published 19 days ago • 215

Towards Thinking-Optimal Scaling of Test-Time Compute for LLM Reasoning

Paper • 2502.18080 • Published 27 days ago • 2

upvoted a collection 14 days ago

YuLan-Mini

A highly capable 2.4B lightweight LLM using only 1T pre-training data with all details. • 6 items • Updated 7 days ago • 15

upvoted a collection 18 days ago

Instella ✨

Announcing Instella, a series of 3 billion parameter language models developed by AMD, trained from scratch on 128 Instinct MI300X GPUs. • 5 items • Updated 19 days ago • 5

upvoted a paper 20 days ago

Multi-Turn Code Generation Through Single-Step Rewards

Paper • 2502.20380 • Published 25 days ago • 30

upvoted a paper 21 days ago

Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V

Paper • 2310.11441 • Published Oct 17, 2023 • 28