Add dense_npu.sh for megatron lora training in huawei npu

examples/ascend/train/qwen3_lora_megatron/dense_npu.sh

@@ -0,0 +1,38 @@
+NPROC_PER_NODE=2 \
+ASCEND_RT_VISIBLE_DEVICES=0,1 \
+megatron sft \
+    --model Qwen/Qwen2.5-7B-Instruct \
+    --load_safetensors true \
+    --save_safetensors true \
+    --dataset 'AI-ModelScope/alpaca-gpt4-data-zh#500' \
+              'AI-ModelScope/alpaca-gpt4-data-en#500' \
+              'swift/self-cognition#500' \
+    --train_type lora \
+    --lora_rank 8 \
+    --lora_alpha 32 \
+    --target_modules all-linear \
+    --tensor_model_parallel_size 2 \
+    --sequence_parallel true \
+    --micro_batch_size 1 \
+    --global_batch_size 2 \
+    --recompute_granularity full \
+    --recompute_method uniform \
+    --recompute_num_layers 1 \
+    --finetune true \
+    --cross_entropy_loss_fusion true \
+    --lr 1e-4 \
+    --lr_warmup_fraction 0.05 \
+    --min_lr 1e-5 \
+    --max_epochs 1 \
+    --save megatron_output/Qwen2.5-7B-Instruct \
+    --save_interval 100 \
+    --max_length 2048 \
+    --system 'You are a helpful assistant.' \
+    --num_workers 4 \
+    --no_save_optim true \
+    --no_save_rng true \
+    --dataset_num_proc 4 \
+    --no_gradient_accumulation_fusion true \
+    --no_masked_softmax_fusion true \
+    --model_author swift \
+    --model_name swift-robot