chore: import upstream snapshot with attribution

examples/train/seq_cls/bert/deploy.sh

@@ -0,0 +1,11 @@
+CUDA_VISIBLE_DEVICES=0 \
+swift deploy \
+    --adapters output/vx-xxx/checkpoint-xxx \
+    --served_model_name bert-base-chinese \
+    --truncation_strategy right \
+    --max_length 512
+
+# curl http://localhost:8000/v1/chat/completions -H "Content-Type: application/json" -d '{
+# "model": "bert-base-chinese",
+# "messages": [{"role": "user", "content": "包装差，容易被调包。"}]
+# }'

examples/train/seq_cls/bert/infer.sh

@@ -0,0 +1,7 @@
+CUDA_VISIBLE_DEVICES=0 \
+swift infer \
+    --adapters output/vx-xxx/checkpoint-xxx \
+    --load_data_args true \
+    --max_batch_size 16 \
+    --truncation_strategy right \
+    --max_length 512

examples/train/seq_cls/bert/sft.sh

@@ -0,0 +1,30 @@
+# If `num_labels` is provided, it will be considered a classification task,
+# and AutoModelForSequenceClassification will be used to load the model.
+# The BERT model does not require templates, so it can usually be used without registration.
+CUDA_VISIBLE_DEVICES=0 \
+swift sft \
+    --model AI-ModelScope/bert-base-chinese \
+    --tuner_type lora \
+    --dataset 'DAMO_NLP/jd:cls#2000' \
+    --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-4 \
+    --lora_rank 8 \
+    --lora_alpha 32 \
+    --target_modules all-linear \
+    --gradient_accumulation_steps 16 \
+    --eval_steps 50 \
+    --save_steps 50 \
+    --save_total_limit 2 \
+    --logging_steps 5 \
+    --max_length 512 \
+    --truncation_strategy right \
+    --output_dir output \
+    --warmup_ratio 0.05 \
+    --dataloader_num_workers 4 \
+    --num_labels 2 \
+    --task_type seq_cls