Blog

BigCode and ServiceNow release StarCoder 2, a family of open-source code generation models with 16K context and support for 600+ programming languages.

Discover how DeepSeekMath-7B uses GRPO and a massive 120B token corpus to rival industry giants in mathematical reasoning.

DeepSeek-MoE marks a historical milestone in open-source AI, proving that sparse Mixture-of-Experts models can match dense giants with a fraction of the compute.

Korean startup Upstage releases SOLAR 10.7B, a groundbreaking open-source model that topped the HuggingFace Open LLM Leaderboard upon release.

Mistral AI's groundbreaking 46.7B parameter MoE model delivers GPT-3.5-level performance with just 12.9B active parameters.

Google DeepMind's Gemini 1.0 marks a pivotal moment in AI history with its natively multimodal architecture that processes text, images, audio, and video simultaneously.

DeepSeek marks a historical milestone in the open-source community with the release of DeepSeek-LLM, challenging the dominance of closed-source giants.

Discover how Nous Research's Hermes 2 models are setting new benchmarks for open-source language models with superior instruction following and community-driven improvements.

01.AI's Yi 34B model delivers exceptional bilingual performance, competing directly with larger models like Llama 2 70B while maintaining cost efficiency.