Type something to search...
to navigateto selectESC to close

Pre training

Qwen2.5: Redefining Efficiency in Large Language Models

Qwen2.5: Redefining Efficiency in Large Language Models

Scaling Smarter and Learning Better with Reinforcement Learning A New Era of Language Models: Introducing Qwen2.5 Building on the breakthroughs in large language models (LLMs), **Qwe

Read More
SmolLM2: Very Good Alternatives to Qwen2.5 and Llama 3.2

SmolLM2: Very Good Alternatives to Qwen2.5 and Llama 3.2

And it's fully open! Hugging Face has doubled down on their SmolLM initiative. They released SmolLM2: 1.7B, 360M, and 135M models trained on 11T tokens (against 1T for SmolLM). They release

Read More