Comment on Apple to use Chinese giant Alibaba’s AI in iPhones
IndustryStandard@lemmy.world 1 week agoDeepseek R1 is currently the selfhosting model to use
Comment on Apple to use Chinese giant Alibaba’s AI in iPhones
IndustryStandard@lemmy.world 1 week agoDeepseek R1 is currently the selfhosting model to use
brucethemoose@lemmy.world 1 week ago
Some of the distillations are trained on top of Qwen 2.5.
And for some cases, FuseAI (a special merge of several thinking models), Qwen Coder, EVA-Gutenberg Qwen, or some other specialized models do a better job than Deepseek 32B in certain niches.