Get the latest tech news

Qwen2 LLM Released

GITHUB HUGGING FACE MODELSCOPE DEMO DISCORD Introduction After months of efforts, we are pleased to announce the evolution from Qwen1.5 to Qwen2. This time, we bring to you: Pretrained and instruction-tuned models of 5 sizes, including Qwen2-0.5B, Qwen2-1.5B, Qwen2-7B, Qwen2-57B-A14B, and Qwen2-72B; Having been trained on data in 27 additional languages besides English and Chinese; State-of-the-art performance in a large number of benchmark evaluations; Significantly improved performance in coding and mathematics; Extended context length support up to 128K tokens with Qwen2-7B-Instruct and Qwen2-72B-Instruct.

RegionsLanguagesWestern EuropeGerman, French, Spanish, Portuguese, Italian, DutchEastern & Central EuropeRussian, Czech, PolishMiddle EastArabic, Persian, Hebrew, TurkishEastern AsiaJapanese, KoreanSouth-Eastern AsiaVietnamese, Thai, Indonesian, Malay, Lao, Burmese, Cebuano, Khmer, TagalogSouthern AsiaHindi, Bengali, UrduAdditionally, we have devoted significant effort to addressing code-switching, a frequent occurrence in multilingual evaluation. The table below presents the proportion of harmful responses generated by large models for four categories of multilingual unsafe querys(Illegal Activity, Fraud, Pornography, Privacy Violence). For a long time, a lot of friends have been supporting the development of Qwen, including finetuning ( Axolotl, Llama-Factory, Firefly, Swift, XTuner), quantization ( AutoGPTQ, AutoAWQ, Neural Compressor), deployment ( vLLM, SGL, SkyPilot, TensorRT-LLM, OpenVino, TGI), API platforms ( Together, Fireworks, OpenRouter), local run ( MLX, Llama.cpp, Ollama, LM Studio), Agent and RAG Frameworks ( LlamaIndex, CrewAI, OpenDevin) , Evaluation ( LMSys, OpenCompass, Open LLM Leaderboard), model training ( Dolphin, Openbuddy) etc.

Get the Android app