chore: import upstream snapshot with attribution

examples/train/full/dft.sh

@@ -0,0 +1,23 @@
+# 4*80G
+# exp: https://github.com/modelscope/ms-swift/pull/5355
+CUDA_VISIBLE_DEVICES=0,1,2,3 \
+NPROC_PER_NODE=4 \
+swift sft \
+    --model Qwen/Qwen2.5-Math-1.5B \
+    --tuner_type full \
+    --dataset AI-MO/NuminaMath-CoT#100000 \
+    --load_from_cache_file true \
+    --torch_dtype bfloat16 \
+    --enable_dft_loss true \
+    --num_train_epochs 1 \
+    --per_device_train_batch_size 8 \
+    --learning_rate 5e-5 \
+    --gradient_accumulation_steps 32 \
+    --save_total_limit 2 \
+    --logging_steps 5 \
+    --max_length 2048 \
+    --output_dir output \
+    --system 'You are a helpful assistant.' \
+    --warmup_ratio 0.1 \
+    --deepspeed zero2 \
+    --dataloader_num_workers 4

examples/train/full/infer.sh

@@ -0,0 +1,7 @@
+# If you are using the validation set for inference, add the parameter `--load_data_args true`.
+CUDA_VISIBLE_DEVICES=0 \
+swift infer \
+    --model output/vx-xxx/checkpoint-xxx \
+    --stream true \
+    --temperature 0 \
+    --max_new_tokens 2048

examples/train/full/qwen2_5_32b.sh

@@ -0,0 +1,29 @@
+# 8 * 80GiB
+PYTORCH_CUDA_ALLOC_CONF='expandable_segments:True' \
+NPROC_PER_NODE=8 \
+CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 \
+swift sft \
+    --model Qwen/Qwen2.5-32B \
+    --tuner_type full \
+    --dataset 'liucong/Chinese-DeepSeek-R1-Distill-data-110k-SFT' \
+    --torch_dtype bfloat16 \
+    --max_steps 2000 \
+    --streaming true \
+    --per_device_train_batch_size 1 \
+    --per_device_eval_batch_size 1 \
+    --learning_rate 1e-5 \
+    --gradient_accumulation_steps 2 \
+    --packing true \
+    --eval_steps 200 \
+    --save_steps 200 \
+    --logging_steps 5 \
+    --max_length 8192 \
+    --warmup_ratio 0.05 \
+    --dataloader_num_workers 8 \
+    --dataset_num_proc 8 \
+    --save_total_limit 2 \
+    --save_only_model true \
+    --output_dir output/Qwen2.5-32B \
+    --deepspeed zero3 \
+    --use_liger_kernel true \
+    --attn_impl flash_attn

examples/train/full/train.sh

@@ -0,0 +1,25 @@
+# 76GiB
+CUDA_VISIBLE_DEVICES=0 \
+swift sft \
+    --model Qwen/Qwen2.5-7B-Instruct \
+    --tuner_type full \
+    --dataset 'AI-ModelScope/alpaca-gpt4-data-zh#500' \
+              'AI-ModelScope/alpaca-gpt4-data-en#500' \
+              'swift/self-cognition#500' \
+    --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 16 \
+    --eval_steps 100 \
+    --save_steps 100 \
+    --save_total_limit 2 \
+    --logging_steps 5 \
+    --max_length 2048 \
+    --output_dir output \
+    --system 'You are a helpful assistant.' \
+    --warmup_ratio 0.05 \
+    --dataloader_num_workers 4 \
+    --model_author swift \
+    --model_name swift-robot