diff --git a/examples/server/README.md b/examples/server/README.md
index 824fd5194..fbd2be8d4 100644
--- a/examples/server/README.md
+++ b/examples/server/README.md
@@ -154,7 +154,7 @@ node .
 
     `ignore_eos`: Ignore end of stream token and continue generating (default: false).
 
-    `logit_bias`: Modify the likelihood of a token appearing in the generated text completion. For example, use `logit-bias: [[15043,1]]` to increase the likelihood of the token 'Hello', or `logit-bias: [[15043,-1]]` to decrease its likelihood. Setting the value to false, `logit-bias: [[15043,false]]` ensures that the token `Hello` is never produced (default: []).
+    `logit_bias`: Modify the likelihood of a token appearing in the generated text completion. For example, use `"logit_bias": [[15043,1.0]]` to increase the likelihood of the token 'Hello', or `"logit_bias": [[15043,-1.0]]` to decrease its likelihood. Setting the value to false, `"logit_bias": [[15043,false]]` ensures that the token `Hello` is never produced (default: []).
 
 -   **POST** `/tokenize`: Tokenize a given text.
 
diff --git a/examples/server/server.cpp b/examples/server/server.cpp
index f28308267..8a1ad0086 100644
--- a/examples/server/server.cpp
+++ b/examples/server/server.cpp
@@ -700,7 +700,7 @@ static void parse_options_completion(const json & body, llama_server_context & l
             if (el.is_array() && el.size() == 2 && el[0].is_number_integer()) {
                 llama_token tok = el[0].get<llama_token>();
                 if (tok >= 0 && tok < n_vocab) {
-                    if (el[1].is_number_float()) {
+                    if (el[1].is_number()) {
                         llama.params.logit_bias[tok] = el[1].get<float>();
                     } else if (el[1].is_boolean() && !el[1].get<bool>()) {
                         llama.params.logit_bias[tok] = -INFINITY;