Jampants
@jampants.bsky.social
Have you seen this in relation to DeepSeek? A dynamic version for deepseek that quantizes the full model down - looks interesting. unsloth.ai/blog/deepsee...
Run DeepSeek-R1 Dynamic 1.58-bit
DeepSeek R-1 is the most powerful open-source reasoning model that performs on par with OpenAI's o1 model.
Run the 1.58-bit Dynamic GGUF version by Unsloth.
unsloth.ai
January 28, 2025 at 9:36 AM
Have you seen this in relation to DeepSeek? A dynamic version for deepseek that quantizes the full model down - looks interesting. unsloth.ai/blog/deepsee...
Maybe try using it, you might begin to understand it better and widen your views.
December 6, 2024 at 8:42 PM
Maybe try using it, you might begin to understand it better and widen your views.
Got a link to that article you wrote from 13 years ago that you quote here ?
November 16, 2024 at 10:08 AM
Got a link to that article you wrote from 13 years ago that you quote here ?