chore: import upstream snapshot with attribution

examples/models/gemma4/diffusion_gemma.sh

@@ -0,0 +1,47 @@
+# 2 * 60GiB
+# This is just a demo for DiffusionGemma training.
+# Notes:
+# 1. Currently only --per_device_train_batch_size 1 is supported,
+# and the response length of a single sample must be less than config.canvas_length.
+# 2. --gradient_checkpointing false must be set. DiffusionGemma's encoder passes
+# KV to the decoder via DynamicCache, and gradient checkpointing causes errors
+# when recomputing the forward pass during backward.
+# 3. For customizing the specific training loss, refer to:
+# https://github.com/modelscope/ms-swift/blob/104048e374b954b4df6961f83f77392031f38fb0/swift/template/templates/gemma.py#L386-L428
+CUDA_VISIBLE_DEVICES=0,1 \
+NPROC_PER_NODE=2 \
+swift sft \
+    --model google/diffusiongemma-26B-A4B-it \
+    --dataset 'sapientinc/sudoku-extreme-1k' \
+    --load_from_cache_file true \
+    --split_dataset_ratio 0.01 \
+    --tuner_type lora \
+    --torch_dtype bfloat16 \
+    --per_device_train_batch_size 1 \
+    --per_device_eval_batch_size 1 \
+    --learning_rate 1e-4 \
+    --num_train_epochs 3 \
+    --loss_scale ignore_empty_think \
+    --gradient_checkpointing false \
+    --lora_rank 8 \
+    --lora_alpha 32 \
+    --target_modules all-linear \
+    --freeze_vit true \
+    --freeze_aligner true \
+    --gradient_accumulation_steps 4 \
+    --eval_steps 100 \
+    --save_steps 100 \
+    --save_total_limit 2 \
+    --logging_steps 5 \
+    --max_length 4096 \
+    --output_dir output \
+    --warmup_ratio 0.05 \
+    --dataset_num_proc 4 \
+    --deepspeed zero2 \
+    --dataloader_num_workers 4
+
+CUDA_VISIBLE_DEVICES=0 \
+swift infer \
+    --adapters output/vx-xxx/checkpoint-xxx \
+    --load_data_args true \
+    --enable_thinking false

examples/models/gemma4/gemma4_unified.sh

@@ -0,0 +1,49 @@
+# 4 * 65GiB
+# Due to the use of group_by_length, the data is not sufficiently shuffled,
+# which may cause fluctuations in the loss curve. Please adjust the parameters accordingly.
+PYTORCH_CUDA_ALLOC_CONF='expandable_segments:True' \
+NPROC_PER_NODE=4 \
+CUDA_VISIBLE_DEVICES=0,1,2,3 \
+megatron sft \
+    --model google/gemma-4-12B-it \
+    --save_safetensors true \
+    --dataset 'AI-ModelScope/LaTeX_OCR:human_handwrite#2000' \
+    --load_from_cache_file true \
+    --add_non_thinking_prefix true \
+    --loss_scale ignore_empty_think \
+    --split_dataset_ratio 0.01 \
+    --tuner_type full \
+    --tensor_model_parallel_size 4 \
+    --micro_batch_size 16 \
+    --global_batch_size 16 \
+    --recompute_granularity full \
+    --recompute_method uniform \
+    --recompute_num_layers 1 \
+    --num_train_epochs 1 \
+    --finetune true \
+    --freeze_llm false \
+    --freeze_vit true \
+    --freeze_aligner true \
+    --cross_entropy_loss_fusion true \
+    --lr 1e-5 \
+    --lr_warmup_fraction 0.05 \
+    --min_lr 1e-6 \
+    --output_dir megatron_output/gemma-4-12B-it \
+    --eval_steps 500 \
+    --save_steps 500 \
+    --max_length 4096 \
+    --dataloader_num_workers 8 \
+    --dataset_num_proc 8 \
+    --no_save_optim true \
+    --no_save_rng true \
+    --sequence_parallel true \
+    --attention_backend unfused \
+    --group_by_length true \
+    --padding_free false
+
+# CUDA_VISIBLE_DEVICES=0 swift infer \
+#     --model megatron_output/gemma-4-12B-it/vx-xxx/checkpoint-xxx \
+#     --stream true \
+#     --enable_thinking false \
+#     --load_data_args true \
+#     --max_new_tokens 2048

examples/models/gemma4/mcore.sh

@@ -0,0 +1,60 @@
+# 8 * 80GiB
+# Due to the use of group_by_length, the data is not sufficiently shuffled,
+# which may cause fluctuations in the loss curve. Please adjust the parameters accordingly.
+PYTORCH_CUDA_ALLOC_CONF='expandable_segments:True' \
+NPROC_PER_NODE=8 \
+CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 \
+megatron sft \
+    --model google/gemma-4-26B-A4B-it \
+    --save_safetensors true \
+    --dataset 'AI-ModelScope/alpaca-gpt4-data-zh#500' \
+              'AI-ModelScope/alpaca-gpt4-data-en#500' \
+              'swift/self-cognition#500' \
+              'AI-ModelScope/LaTeX_OCR:human_handwrite#2000' \
+    --load_from_cache_file true \
+    --add_non_thinking_prefix true \
+    --loss_scale ignore_empty_think \
+    --split_dataset_ratio 0.01 \
+    --tuner_type full \
+    --tensor_model_parallel_size 2 \
+    --expert_model_parallel_size 4 \
+    --pipeline_model_parallel_size 2 \
+    --moe_permute_fusion true \
+    --moe_grouped_gemm true \
+    --moe_shared_expert_overlap true \
+    --moe_aux_loss_coeff 1e-6 \
+    --micro_batch_size 8 \
+    --global_batch_size 16 \
+    --recompute_granularity full \
+    --recompute_method uniform \
+    --recompute_num_layers 1 \
+    --num_train_epochs 1 \
+    --finetune true \
+    --freeze_llm false \
+    --freeze_vit true \
+    --freeze_aligner true \
+    --cross_entropy_loss_fusion true \
+    --lr 1e-5 \
+    --lr_warmup_fraction 0.05 \
+    --min_lr 1e-6 \
+    --output_dir megatron_output/gemma-4-26B-A4B-it \
+    --eval_steps 500 \
+    --save_steps 500 \
+    --max_length 4096 \
+    --dataloader_num_workers 8 \
+    --dataset_num_proc 8 \
+    --no_save_optim true \
+    --no_save_rng true \
+    --sequence_parallel true \
+    --attention_backend unfused \
+    --group_by_length true \
+    --padding_free false \
+    --model_author swift \
+    --model_name swift-robot
+
+# CUDA_VISIBLE_DEVICES=0 swift infer \
+#     --model megatron_output/gemma-4-26B-A4B-it/vx-xxx/checkpoint-xxx \
+#     --stream true \
+#     --enable_thinking false \
+#     --load_data_args true \
+#     --max_new_tokens 2048

examples/models/gemma4/train.sh

@@ -0,0 +1,35 @@
+NPROC_PER_NODE=2 \
+CUDA_VISIBLE_DEVICES=0,1 \
+swift sft \
+    --model google/gemma-4-E2B-it \
+    --dataset 'AI-ModelScope/LaTeX_OCR:human_handwrite#2000' \
+    --load_from_cache_file true \
+    --split_dataset_ratio 0.01 \
+    --tuner_type lora \
+    --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 \
+    --freeze_vit true \
+    --freeze_aligner true \
+    --gradient_accumulation_steps 16 \
+    --eval_steps 50 \
+    --save_steps 50 \
+    --save_total_limit 2 \
+    --logging_steps 5 \
+    --max_length 4096 \
+    --output_dir output \
+    --warmup_ratio 0.05 \
+    --deepspeed zero2 \
+    --dataset_num_proc 4 \
+    --dataloader_num_workers 4
+
+# CUDA_VISIBLE_DEVICES=0 \
+# swift infer \
+#     --adapters output/vx-xxx/checkpoint-xxx \
+#     --stream true \
+#     --load_data_args true