From 17d82f0a4ece9560600a1f65d46cb70c7c4ed72c Mon Sep 17 00:00:00 2001
From: Christian Risi <75698846+CnF-Gris@users.noreply.github.com>
Date: Thu, 2 Oct 2025 08:48:28 +0200
Subject: [PATCH] Added support to resume workload

---
 Scripts/Training/bpe_trainer_pool.py | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/Scripts/Training/bpe_trainer_pool.py b/Scripts/Training/bpe_trainer_pool.py
index 5c7ab6e..966816d 100644
--- a/Scripts/Training/bpe_trainer_pool.py
+++ b/Scripts/Training/bpe_trainer_pool.py
@@ -72,11 +72,17 @@ def train(args: ProgramArgs):
     VOCABULARY_PATH = Path(args.output_file)
     CACHE_PATH = Path(args.cache_file)
 
+    start_bpe = BPE.NanoSocratesBPE()
+    if CACHE_PATH.is_file():
+        voc = BPE.load_nanos_vocabulary(CACHE_PATH)
+        start_bpe = BPE.NanoSocratesBPE(voc)
+
     print(f"Training BPE")
 
     BPE_ENCODER = TRAINER.trainBPE(
         DATASET_PATH,
-        CACHE_PATH
+        CACHE_PATH,
+        start_bpe
     )
 
     VOCABULARY = BPE_ENCODER.vocabulary