Articles

granite3-moe
Enterprise AI Evolution: Granite3 Moe's Low-Latency Breakthrough

Published on 2024-10-21
nemotron
NVIDIA's Llama-3.1-Nemotron-70B-Instruct: Advancing Helpfulness and Human Alignment in LLMs

Published on 2024-10-17
shieldgemma
ShieldGemma: Pioneering Safe Content Moderation with Open-Source AI Models

Published on 2024-10-11
llama-guard3
Advancing Real-Time Content Safety with Llama Guard3

Published on 2024-10-11
llama3.2
Advancing Multilingual Dialogue with Llama3.2's Agentic Capabilities

Published on 2024-09-25
qwen2.5-coder
Qwen2.5 Coder: Advancing Code Generation and Multi-Language Support

Published on 2024-09-19
qwen2.5-coder
Qwen2.5 Coder: Revolutionizing Open-Source Coding

Published on 2024-09-19
qwen2.5
Qwen2.5: Advancing Factual Knowledge, Coding, and Multilingual Capabilities

Published on 2024-09-18
nemotron-mini
NVIDIA Nemotron Mini: Enhancing Roleplay, RAG, and On-Device Performance

Published on 2024-09-18
mistral-small
Mistral Small 3: Advancing Open-Source LLMs with Efficiency and Scalability

Published on 2024-09-18
solar-pro
Solar Pro: Redefining Single-GPU Efficiency in Large Language Models

Published on 2024-09-18
bespoke-minicheck
Bespoke-MiniCheck: Pioneering Efficient Fact-Checking with State-of-the-Art Accuracy

Published on 2024-09-18