May need --override-kv tokenizer.ggml.eot_token_id=int:151336

README.md

@@ -157,6 +157,7 @@ $ ./build/bin/llama-server \
     -fa -fmoe \
     -ctk q8_0 -ctv q8_0 \
     --chat-template chatglm4 \
+    --override-kv tokenizer.ggml.eot_token_id=int:151336 \
     -ub 4096 -b 4096 \
     -ngl 99 \
     -ot exps=CPU \