Qwen-2.5 Technical Report
Free while signed in. Answers cite the passages they came from.
First page
The curator’s take
Alibaba releases Qwen2.5, a new series of LLMs trained on 18T tokens, offering both open-weight models like Qwen2.5-72B and proprietary MoE variants that achieve competitive performance against larger models like Llama-3 and GPT-4.
Every Monday
Get next week’s papers.
The same picks and the same summaries, in your inbox. Free, and 176 issues deep.
Subscribe on Substack