cmedina/agenx-lora-training
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: tokenizer -> processing_class SFTTrainer API change

Browse Source
This commit is contained in:
Christian Medina
2026-06-30 20:38:31 -04:00
parent 9d5d4eebc7
commit 83ba987840
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
training/scripts/train.py
View File

@@ -99,7 +99,7 @@ def train(config_path):
trainer = SFTTrainer( trainer = SFTTrainer(
model=model, model=model,
tokenizer=tokenizer, processing_class=tokenizer,
train_dataset=dataset["train"], train_dataset=dataset["train"],
eval_dataset=dataset["test"], eval_dataset=dataset["test"],
args=training_args, args=training_args,