AMD 推出全开源 3B 语言模型，媲美 Qwen2.5-3B
品玩3月7日讯，据 HuggingFace 页面显示，AMD宣布推出Instella，这是一个在AMD Instinct™ MI300X GPU上从头开始训练的完全开放的最先进的30亿参数语言模型系列。
与 Llama-3.2-3B、Gemma-2-2B 和 Qwen-2.5-3B 等最先进的开放式重量模型（包括经过指令调整的对应模型）相比，Instella 模型的性能优于现有的类似规模的完全开放式模型，并实现了具有竞争力的性能。
该模型现已在 AMD 平台上开源。
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