From a9b3f4a54b544a6e9adde65673533e0154d7767a Mon Sep 17 00:00:00 2001 From: Iwan Kawrakow Date: Wed, 7 Aug 2024 16:49:43 +0300 Subject: iq6_k: WIP (quantize/dequantize) --- include/llama.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/llama.h') diff --git a/include/llama.h b/include/llama.h index a5a2deb1..9ae88060 100644 --- a/include/llama.h +++ b/include/llama.h @@ -174,7 +174,8 @@ extern "C" { LLAMA_FTYPE_MOSTLY_IQ3_K = 39, // except 1d tensors LLAMA_FTYPE_MOSTLY_IQ4_K = 40, // except 1d tensors LLAMA_FTYPE_MOSTLY_IQ5_K = 41, // except 1d tensors - LLAMA_FTYPE_MOSTLY_IQ2_TN = 42, // except 1d tensors + LLAMA_FTYPE_MOSTLY_IQ6_K = 42, // except 1d tensors + LLAMA_FTYPE_MOSTLY_IQ2_TN = 43, // except 1d tensors LLAMA_FTYPE_GUESSED = 1024, // not specified in the model file }; -- cgit v1.2.3