This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
diff --git a/src/llama-quant.cpp b/src/llama-quant.cpp | |
index fb798265..cfa73700 100644 | |
--- a/src/llama-quant.cpp | |
+++ b/src/llama-quant.cpp | |
@@ -187,6 +187,7 @@ static ggml_type llama_tensor_get_type(quantize_state_impl & qs, ggml_type new_t | |
} | |
} else if (ftype == LLAMA_FTYPE_MOSTLY_IQ2_XXS || ftype == LLAMA_FTYPE_MOSTLY_IQ2_XS || ftype == LLAMA_FTYPE_MOSTLY_IQ1_S || | |
ftype == LLAMA_FTYPE_MOSTLY_IQ2_S || ftype == LLAMA_FTYPE_MOSTLY_IQ2_M || ftype == LLAMA_FTYPE_MOSTLY_IQ1_M) { | |
+ bool is_one_bit = (ftype == LLAMA_FTYPE_MOSTLY_IQ1_M || ftype == LLAMA_FTYPE_MOSTLY_IQ1_S); | |
if (name.find("attn_v.weight") != std::string::npos) { |