chore: import upstream snapshot with attribution

examples/models/gpt_oss/internvl3_5_gpt.sh

@@ -0,0 +1,49 @@
+# 8 * 80GiB 4s/it
+PYTORCH_CUDA_ALLOC_CONF='expandable_segments:True' \
+OMP_NUM_THREADS=14 \
+NPROC_PER_NODE=8 \
+CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 \
+megatron sft \
+    --model OpenGVLab/InternVL3_5-GPT-OSS-20B-A4B-Preview \
+    --save_safetensors true \
+    --dataset 'AI-ModelScope/alpaca-gpt4-data-zh#10000' \
+              'AI-ModelScope/LaTeX_OCR:human_handwrite#5000' \
+              'swift/VideoChatGPT:Generic#2000' \
+    --load_from_cache_file true \
+    --split_dataset_ratio 0.01 \
+    --moe_permute_fusion true \
+    --tensor_model_parallel_size 2 \
+    --expert_model_parallel_size 8 \
+    --moe_grouped_gemm true \
+    --moe_shared_expert_overlap true \
+    --moe_aux_loss_coeff 1e-6 \
+    --micro_batch_size 2 \
+    --global_batch_size 16 \
+    --recompute_granularity full \
+    --recompute_method uniform \
+    --recompute_num_layers 1 \
+    --num_train_epochs 1 \
+    --finetune true \
+    --cross_entropy_loss_fusion true \
+    --lr 1e-5 \
+    --lr_warmup_fraction 0.05 \
+    --min_lr 1e-6 \
+    --output_dir megatron_output/InternVL3_5-GPT-OSS-20B-A4B-Preview \
+    --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 \
+    --moe_expert_capacity_factor 2 \
+    --padding_free false \
+    --attention_backend unfused
+
+# CUDA_VISIBLE_DEVICES=0 \
+# swift infer \
+#     --model megatron_output/InternVL3_5-GPT-OSS-20B-A4B-Preview/vx-xxx/checkpoint-xxx \
+#     --stream true \
+#     --load_data_args true \
+#     --max_new_tokens 512

examples/models/gpt_oss/mcore.sh

@@ -0,0 +1,50 @@
+# 2 * 40GiB
+# dataset format: https://github.com/modelscope/ms-swift/pull/5277
+PYTORCH_CUDA_ALLOC_CONF='expandable_segments:True' \
+NPROC_PER_NODE=2 \
+CUDA_VISIBLE_DEVICES=0,1 \
+megatron sft \
+    --model openai-mirror/gpt-oss-20b \
+    --save_safetensors true \
+    --merge_lora true \
+    --dataset 'AI-ModelScope/alpaca-gpt4-data-zh#500' \
+              'AI-ModelScope/alpaca-gpt4-data-en#500' \
+              'swift/self-cognition#500' \
+    --tuner_type lora \
+    --lora_rank 8 \
+    --lora_alpha 32 \
+    --target_modules all-linear \
+    --expert_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 \
+    --cross_entropy_loss_fusion true \
+    --lr 1e-4 \
+    --lr_warmup_fraction 0.05 \
+    --min_lr 1e-5 \
+    --output_dir megatron_output/gpt-oss-20b \
+    --eval_steps 100 \
+    --save_steps 100 \
+    --max_length 2048 \
+    --dataloader_num_workers 4 \
+    --dataset_num_proc 4 \
+    --no_save_optim true \
+    --no_save_rng true \
+    --sequence_parallel true \
+    --padding_free false \
+    --attention_backend unfused \
+    --model_author swift \
+    --model_name swift-robot
+
+# CUDA_VISIBLE_DEVICES=0 \
+# swift infer \
+#     --model megatron_output/gpt-oss-20b/vx-xxx/checkpoint-xxx \
+#     --stream true

examples/models/gpt_oss/train.sh

@@ -0,0 +1,29 @@
+# 42GB
+# https://github.com/modelscope/ms-swift/pull/5277
+CUDA_VISIBLE_DEVICES=0 \
+swift sft \
+    --model openai-mirror/gpt-oss-20b \
+    --tuner_type lora \
+    --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 \
+    --router_aux_loss_coef 1e-3 \
+    --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 2048 \
+    --output_dir output \
+    --warmup_ratio 0.05 \
+    --dataloader_num_workers 4 \
+    --model_author swift \
+    --model_name swift-robot