AMD推出完全开源的3B参数语言模型Instella，媲美Llama-3.2-3B和Qwen2.5-3B
IT之家 3月6日消息，AMD今日宣布，为Radeon RX 9070系列开源Linux驱动程序，还宣布开源Instella —— 一个完全开源的3B参数语言模型。
AMD Instella代表“完全开源的尖端30亿参数语言模型（LMs）”。这些模型在AMD Instinct MI300X GPU上进行了训练，根据AMD发布的数据，其性能与Llama 3.2 3B、Gemma-2 2B和Qwen 2.5 3B等相媲美。
AMD Instella模型是在Instinct MI300X硬件上从头开始训练的，并且宣称是完全开源的：
完全开源和可访问：模型权重、训练超参数、数据集和代码的完全开源发布，促进人工智能社区内的创新与合作。
IT之家附开源地址如下：
https://github.com/AMD-AIG-AIMA/Instella
Disclaimer: Investing carries risk. This is not financial advice. The above content should not be regarded as an offer, recommendation, or solicitation on acquiring or disposing of any financial products, any associated discussions, comments, or posts by author or other users should not be considered as such either. It is solely for general information purpose only, which does not consider your own investment objectives, financial situations or needs. TTM assumes no responsibility or warranty for the accuracy and completeness of the information, investors should do their own research and may seek professional advice before investing.
Most Discussed
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10