llama : restore intended k-quants mixes for MoE models (#4872)

* Restore intended k-quants quantization mixes for MoE models

* Update Q2_K_S values in the quantize tool

Still using LLaMA-v1 PPL values in the quant description
today does not make much sense. But let's leave this update
for another PR.

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

1 files changed, 1 insertions, 0 deletions

diff --git a/llama.h b/llama.h
index 6fde113f..43d41b8f 100644
--- a/llama.h
+++ b/llama.h
@@ -105,6 +105,7 @@ extern "C" {
         LLAMA_FTYPE_MOSTLY_Q6_K          = 18, // except 1d tensors
         LLAMA_FTYPE_MOSTLY_IQ2_XXS       = 19, // except 1d tensors
         LLAMA_FTYPE_MOSTLY_IQ2_XS        = 20, // except 1d tensors
+        LLAMA_FTYPE_MOSTLY_Q2_K_S        = 21, // except 1d tensors
 
         LLAMA_FTYPE_GUESSED = 1024, // not specified in the model file
     };