AirLLM 2.8T LLM inference with single 4GB GPU
Python chinese-llmchinese-nlpfinetunegenerative-aiinstruct-gptinstruction-setllamallmloraopen-modelsopen-sourceopen-source-modelsqlora
fix script for training
Yu Li3ab3de4e640e
diff --git a/anima_100k/run_longer_training.sh b/anima_100k/run_longer_training.shindex 7eea03d..e6b8efa 100755--- a/anima_100k/run_longer_training.sh+++ b/anima_100k/run_longer_training.sh@@ -18,7 +18,7 @@ mkdir -p $OUTPUT_PATHpython longer_training.py --dataset="DATASET_PATH" \- --dataset_format="FORMAT" \+ --dataset_format="long_data" \--learning_rate 0.0001 \--per_device_train_batch_size 1 \--gradient_accumulation_steps 16 \