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 +1,17 @@
+compute_environment: LOCAL_MACHINE
+deepspeed_config:
+    deepspeed_multinode_launcher: standard
+    gradient_accumulation_steps: 16
+    offload_optimizer_device: none
+    offload_param_device: none
+    zero3_init_flag: false
+    zero_stage: 3
+distributed_type: DEEPSPEED
+main_process_ip: 'xxx.xxx.xxx.xxx'
+main_process_port: 29500
+main_training_function: main
+mixed_precision: bf16
+num_machines: 2
+num_processes: 8  # world size
+rdzv_backend: static
+use_cpu: false
@@ -0,0 +1,18 @@
+CUDA_VISIBLE_DEVICES=0,1,2,3 \
+accelerate launch --config_file ./examples/train/multi-node/accelerate/multi_node.yaml --machine_rank 0 \
+    swift/cli/sft.py \
+    --model Qwen/Qwen2.5-7B-Instruct \
+    --tuner_type lora \
+    --torch_dtype bfloat16 \
+    --dataset 'swift/self-cognition#1000' \
+    --num_train_epochs 1 \
+    --lora_rank 8 \
+    --lora_alpha 32 \
+    --learning_rate 1e-4 \
+    --gradient_accumulation_steps 16 \
+    --eval_steps 100 \
+    --save_steps 100 \
+    --save_total_limit 2 \
+    --logging_steps 5 \
+    --model_author swift \
+    --model_name swift-robot
@@ -0,0 +1,18 @@
+CUDA_VISIBLE_DEVICES=0,1,2,3 \
+accelerate launch --config_file ./examples/train/multi-node/accelerate/multi_node.yaml --machine_rank 1 \
+    swift/cli/sft.py \
+    --model Qwen/Qwen2.5-7B-Instruct \
+    --tuner_type lora \
+    --torch_dtype bfloat16 \
+    --dataset 'swift/self-cognition#1000' \
+    --num_train_epochs 1 \
+    --lora_rank 8 \
+    --lora_alpha 32 \
+    --learning_rate 1e-4 \
+    --gradient_accumulation_steps 16 \
+    --eval_steps 100 \
+    --save_steps 100 \
+    --save_total_limit 2 \
+    --logging_steps 5 \
+    --model_author swift \
+    --model_name swift-robot