From 73e61d5b755f371864f928afafa31ffc0c15a008 Mon Sep 17 00:00:00 2001
From: Georgi Gerganov <ggerganov@gmail.com>
Date: Mon, 16 Feb 2026 10:30:10 +0200
Subject: [PATCH] rename

---
 examples/llama-eval/README.md                            | 2 +-
 examples/llama-eval/{llama-eval-new.py => llama-eval.py} | 8 ++++----
 2 files changed, 5 insertions(+), 5 deletions(-)
 rename examples/llama-eval/{llama-eval-new.py => llama-eval.py} (100%)

diff --git a/examples/llama-eval/README.md b/examples/llama-eval/README.md
index 1c96cc6a1f..89408db823 100644
--- a/examples/llama-eval/README.md
+++ b/examples/llama-eval/README.md
@@ -14,7 +14,7 @@ Simple evaluation tool for llama.cpp with support for multiple datasets.
 ## Usage
 
 ```bash
-python llama-eval-new.py \
+python llama-eval.py \
   --server http://127.0.0.1:8013 \
   --model gpt-oss-20b-hf-low \
   --judge-model gpt-oss-20b-hf-medium \
diff --git a/examples/llama-eval/llama-eval-new.py b/examples/llama-eval/llama-eval.py
similarity index 100%
rename from examples/llama-eval/llama-eval-new.py
rename to examples/llama-eval/llama-eval.py
index eacbe3d887..7396261bff 100755
--- a/examples/llama-eval/llama-eval-new.py
+++ b/examples/llama-eval/llama-eval.py
@@ -460,15 +460,15 @@ class Processor:
 
         print(f"\nProcessing {n_cases} {self.dataset_type.upper()} questions...")
         print(f"Server: {self.server_url} (model: {self.model_name})")
-        print(f"Threads: {self.threads}")
-        print(f"Max tokens: {self.n_predict}")
-        print(f"Seed: {self.seed}")
-        print(f"Sampling: temp={self.sampling_config.get('temperature', 'skip')}, top-k={self.sampling_config.get('top_k', 'skip')}, top-p={self.sampling_config.get('top_p', 'skip')}, min-p={self.sampling_config.get('min_p', 'skip')}")
         print(f"Grader: {self.grader.grader_type}", end="")
         if self.grader.grader_type == "llm":
             judge_model = self.judge_model_name if self.judge_model_name else self.model_name
             print(f" (judge server: {self.judge_server_url}, model: {judge_model})", end="")
         print()
+        print(f"Threads: {self.threads}")
+        print(f"Max tokens: {self.n_predict}")
+        print(f"Seed: {self.seed}")
+        print(f"Sampling: temp={self.sampling_config.get('temperature', 'skip')}, top-k={self.sampling_config.get('top_k', 'skip')}, top-p={self.sampling_config.get('top_p', 'skip')}, min-p={self.sampling_config.get('min_p', 'skip')}")
         print()
 
         dataset_size = len(self.dataset.questions)