chore: import upstream snapshot with attribution

2026-07-13 13:34:58 +08:00
commit a203934033
1368 changed files with 175001 additions and 0 deletions
@@ -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