chore: import upstream snapshot with attribution

2026-07-13 13:34:58 +08:00
commit a203934033
1368 changed files with 175001 additions and 0 deletions
@@ -0,0 +1,27 @@
+# For more information, visit: https://www.aliyun.com/activity/bigdata/pai-dlc
+# https://help.aliyun.com/zh/pai/user-guide/general-environment-variables
+NNODES=$WORLD_SIZE \
+NODE_RANK=$RANK \
+swift sft \
+    --model Qwen/Qwen2.5-7B-Instruct \
+    --tuner_type full \
+    --dataset 'AI-ModelScope/alpaca-gpt4-data-zh#20000' \
+              'AI-ModelScope/alpaca-gpt4-data-en#20000' \
+    --load_from_cache_file true \
+    --split_dataset_ratio 0.01 \
+    --torch_dtype bfloat16 \
+    --num_train_epochs 1 \
+    --per_device_train_batch_size 1 \
+    --per_device_eval_batch_size 1 \
+    --learning_rate 1e-5 \
+    --gradient_accumulation_steps 4 \
+    --eval_steps 100 \
+    --save_steps 100 \
+    --save_total_limit 2 \
+    --logging_steps 5 \
+    --max_length 8192 \
+    --output_dir output \
+    --system 'You are a helpful assistant.' \
+    --warmup_ratio 0.05 \
+    --dataloader_num_workers 4 \
+    --deepspeed zero2