llama.cpp support
#1
by
cpumaxx
- opened
Hello, is the deepseek-ai team going to help implement support for these new models in llama.cpp? Both for correct conversion to GGUF format and running the model?
+1
+1
+1
+1 its deepseek-1.3B model is the best small model to code, this V2 version would be even better for sure! Please deepseek-1.3B-V2 pre-trained.
+1