Re:DeepSeek-R1 with Dynamic 1.58-bit Quantization
by woadwarrior01 on Tuesday January 28, 2025 @09:37AM
(#42852789)
Yeah, they're so clear in fact that they call the distilled models "R1" in the url and everywhere on the page[1], instead of using the "DeepSeek-R1-Distill-" prefix, as DeepSeek themselves do[2].
[1]: https://ollama.com/library/deepseek-r1
[2]: https://github.com/deepseek-ai/DeepSeek-R1#deepseek-r1-disti...