gpt-2 : fix qunatize tool to quantize the "lm_head" tensor

diff --git a/examples/gpt-2/quantize.cpp b/examples/gpt-2/quantize.cpp
index 3cc48ea3909dbe6fb9b8f23f1a6416cafce6c991..693b0787cb6701118c02911e1bce146dc331f21b 100644 (file)
--- a/examples/gpt-2/quantize.cpp
+++ b/examples/gpt-2/quantize.cpp
@@ -162,6 +162,7 @@ bool gpt2_model_quantize(const std::string & fname_inp, const std::string & fnam
             // regexes of tensor names to be quantized
             const std::vector<std::string> k_names = {
                 "model/wte",
+                "model/lm_head",
                 "model/h.*/attn/c_attn/w",
                 "model/h.*/attn/c_proj/w",
                 "model/h.*/mlp/c_fc/w",