chore: import upstream snapshot with attribution

examples/megatron/multimodal/dense/dpo.sh

@@ -0,0 +1,41 @@
+# 4 * 50GiB 14s/it
+PYTORCH_CUDA_ALLOC_CONF='expandable_segments:True' \
+NPROC_PER_NODE=4 \
+MAX_PIXELS=1003520 \
+CUDA_VISIBLE_DEVICES=0,1,2,3 \
+megatron rlhf \
+    --rlhf_type dpo \
+    --model Qwen/Qwen2.5-VL-7B-Instruct \
+    --save_safetensors true \
+    --dataset 'swift/RLAIF-V-Dataset#20000' \
+    --load_from_cache_file true \
+    --tuner_type full \
+    --tensor_model_parallel_size 4 \
+    --sequence_parallel true \
+    --freeze_llm false \
+    --freeze_vit true \
+    --freeze_aligner true \
+    --packing true \
+    --split_dataset_ratio 0.01 \
+    --micro_batch_size 1 \
+    --global_batch_size 4 \
+    --recompute_granularity full \
+    --recompute_method uniform \
+    --recompute_num_layers 1 \
+    --finetune true \
+    --cross_entropy_loss_fusion true \
+    --lr 1e-5 \
+    --lr_warmup_fraction 0.05 \
+    --min_lr 1e-6 \
+    --num_train_epochs 1 \
+    --output_dir megatron_output/Qwen2.5-VL-7B-Instruct \
+    --save_steps 200 \
+    --max_length 8192 \
+    --dataloader_num_workers 4 \
+    --no_save_optim true \
+    --no_save_rng true \
+    --dataset_num_proc 8 \
+    --attention_backend flash \
+    --rpo_alpha 0.1 \
+    --beta 0.1 \
+    --loss_type sigmoid

examples/megatron/multimodal/dense/full.sh

@@ -0,0 +1,35 @@
+# 2 * 72GiB; 4.1s/it
+PYTORCH_CUDA_ALLOC_CONF='expandable_segments:True' \
+NPROC_PER_NODE=2 \
+MAX_PIXELS=1003520 \
+CUDA_VISIBLE_DEVICES=0,1 \
+megatron sft \
+    --model Qwen/Qwen2.5-VL-7B-Instruct \
+    --save_safetensors true \
+    --dataset 'AI-ModelScope/LaTeX_OCR:human_handwrite#5000' \
+    --load_from_cache_file true \
+    --tensor_model_parallel_size 2 \
+    --sequence_parallel true \
+    --packing true \
+    --freeze_llm false \
+    --freeze_vit true \
+    --freeze_aligner true \
+    --split_dataset_ratio 0.01 \
+    --micro_batch_size 1 \
+    --global_batch_size 4 \
+    --recompute_granularity full \
+    --recompute_method uniform \
+    --recompute_num_layers 1 \
+    --finetune true \
+    --cross_entropy_loss_fusion true \
+    --lr 1e-5 \
+    --lr_warmup_fraction 0.05 \
+    --min_lr 1e-6 \
+    --num_train_epochs 1 \
+    --output_dir megatron_output/Qwen2.5-VL-7B-Instruct \
+    --save_steps 200 \
+    --max_length 2048 \
+    --dataloader_num_workers 4 \
+    --no_save_optim true \
+    --no_save_rng true \
+    --dataset_num_proc 8

examples/megatron/multimodal/dense/lora.sh

@@ -0,0 +1,40 @@
+# 2 * 23GiB; 2.3s/it
+PYTORCH_CUDA_ALLOC_CONF='expandable_segments:True' \
+NPROC_PER_NODE=2 \
+MAX_PIXELS=1003520 \
+CUDA_VISIBLE_DEVICES=0,1 \
+megatron sft \
+    --model Qwen/Qwen2.5-VL-7B-Instruct \
+    --save_safetensors true \
+    --merge_lora false \
+    --dataset 'AI-ModelScope/LaTeX_OCR:human_handwrite#5000' \
+    --load_from_cache_file true \
+    --tuner_type lora \
+    --lora_rank 8 \
+    --lora_alpha 32 \
+    --target_modules all-linear \
+    --tensor_model_parallel_size 1 \
+    --sequence_parallel true \
+    --freeze_llm false \
+    --freeze_vit true \
+    --freeze_aligner true \
+    --packing true \
+    --split_dataset_ratio 0.01 \
+    --micro_batch_size 1 \
+    --global_batch_size 4 \
+    --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 \
+    --num_train_epochs 1 \
+    --output_dir megatron_output/Qwen2.5-VL-7B-Instruct \
+    --save_steps 200 \
+    --max_length 2048 \
+    --dataloader_num_workers 4 \
+    --no_save_optim true \
+    --no_save_rng true \
+    --dataset_num_proc 8