From e22fc6f2fac0c3d5f3ecd3ba6b09f7d694014b64 Mon Sep 17 00:00:00 2001
From: svlandeg <svlandeg@github.com>
Date: Mon, 3 Nov 2025 21:46:39 +0100
Subject: [PATCH] few more explicit UTF-8 encodings

---
 dev/gen_synthetic_data.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/dev/gen_synthetic_data.py b/dev/gen_synthetic_data.py
index 13e5f55..73f4ac9 100644
--- a/dev/gen_synthetic_data.py
+++ b/dev/gen_synthetic_data.py
@@ -37,7 +37,7 @@ from concurrent.futures import ThreadPoolExecutor, as_completed
 
 from nanochat.common import get_base_dir
 
-api_key = open("openroutertoken.txt").read().strip()
+api_key = open("openroutertoken.txt", 'r', encoding='utf-8').read().strip()
 
 url = "https://openrouter.ai/api/v1/chat/completions"
 headers = {
@@ -45,7 +45,7 @@ headers = {
   "Content-Type": "application/json"
 }
 
-readme = open("README.md").read().strip()
+readme = open("README.md", 'r', encoding='utf-8').read().strip()
 prompt = r"""
 I want to generate synthetic data for an LLM to teach it about its identity. Here is the identity I want: