diff --git a/common/sampling.cpp b/common/sampling.cpp
index 51647bc8d..a2c6454a9 100644
--- a/common/sampling.cpp
+++ b/common/sampling.cpp
@@ -156,15 +156,15 @@ llama_token llama_sampling_sample(
 
     const int n_vocab = llama_n_vocab(llama_get_model(ctx_main));
 
-    const float   temp                  = params.temp;
-    const int32_t penalty_last_n        = params.penalty_last_n < 0 ? params.n_prev : params.penalty_last_n;
-    const float   penalty_repeat        = params.penalty_repeat;
-    const float   penalty_freq          = params.penalty_freq;
-    const float   penalty_present       = params.penalty_present;
-    const int     mirostat              = params.mirostat;
-    const float   mirostat_tau          = params.mirostat_tau;
-    const float   mirostat_eta          = params.mirostat_eta;
-    const bool    penalize_nl           = params.penalize_nl;
+    const float   temp            = params.temp;
+    const int32_t penalty_last_n  = params.penalty_last_n < 0 ? params.n_prev : params.penalty_last_n;
+    const float   penalty_repeat  = params.penalty_repeat;
+    const float   penalty_freq    = params.penalty_freq;
+    const float   penalty_present = params.penalty_present;
+    const int     mirostat        = params.mirostat;
+    const float   mirostat_tau    = params.mirostat_tau;
+    const float   mirostat_eta    = params.mirostat_eta;
+    const bool    penalize_nl     = params.penalize_nl;
 
     auto & prev = ctx_sampling->prev;
     auto & cur  = ctx_sampling->cur;
diff --git a/common/sampling.h b/common/sampling.h
index 9872b8b38..fdfa9eed1 100644
--- a/common/sampling.h
+++ b/common/sampling.h
@@ -10,23 +10,23 @@
 
 // sampling parameters
 typedef struct llama_sampling_params {
-    int32_t n_prev                = 64;       // number of previous tokens to remember
-    int32_t n_probs               = 0;        // if greater than 0, output the probabilities of top n_probs tokens.
-    int32_t top_k                 = 40;       // <= 0 to use vocab size
-    float   top_p                 = 0.95f;    // 1.0 = disabled
-    float   min_p                 = 0.05f;    // 0.0 = disabled
-    float   tfs_z                 = 1.00f;    // 1.0 = disabled
-    float   typical_p             = 1.00f;    // 1.0 = disabled
-    float   temp                  = 0.80f;    // 1.0 = disabled
-    int32_t penalty_last_n        = 64;       // last n tokens to penalize (0 = disable penalty, -1 = context size)
-    float   penalty_repeat        = 1.10f;    // 1.0 = disabled
-    float   penalty_freq          = 0.00f;    // 0.0 = disabled
-    float   penalty_present       = 0.00f;    // 0.0 = disabled
-    int32_t mirostat              = 0;        // 0 = disabled, 1 = mirostat, 2 = mirostat 2.0
-    float   mirostat_tau          = 5.00f;    // target entropy
-    float   mirostat_eta          = 0.10f;    // learning rate
-    bool    penalize_nl           = true;     // consider newlines as a repeatable token
-    std::string samplers_sequence = "kfypmt"; // top_k, tail_free, typical_p, top_p, min_p, temp
+    int32_t     n_prev                = 64;       // number of previous tokens to remember
+    int32_t     n_probs               = 0;        // if greater than 0, output the probabilities of top n_probs tokens.
+    int32_t     top_k                 = 40;       // <= 0 to use vocab size
+    float       top_p                 = 0.95f;    // 1.0 = disabled
+    float       min_p                 = 0.05f;    // 0.0 = disabled
+    float       tfs_z                 = 1.00f;    // 1.0 = disabled
+    float       typical_p             = 1.00f;    // 1.0 = disabled
+    float       temp                  = 0.80f;    // 1.0 = disabled
+    int32_t     penalty_last_n        = 64;       // last n tokens to penalize (0 = disable penalty, -1 = context size)
+    float       penalty_repeat        = 1.10f;    // 1.0 = disabled
+    float       penalty_freq          = 0.00f;    // 0.0 = disabled
+    float       penalty_present       = 0.00f;    // 0.0 = disabled
+    int32_t     mirostat              = 0;        // 0 = disabled, 1 = mirostat, 2 = mirostat 2.0
+    float       mirostat_tau          = 5.00f;    // target entropy
+    float       mirostat_eta          = 0.10f;    // learning rate
+    bool        penalize_nl           = true;     // consider newlines as a repeatable token
+    std::string samplers_sequence     = "kfypmt"; // top_k, tail_free, typical_p, top_p, min_p, temp
 
     std::string grammar;  // optional BNF-like grammar to constrain sampling