diff --git a/scripts/training/zhizhi_v2/ds_config.json b/scripts/training/zhizhi_v2/ds_config.json
new file mode 100644
index 0000000..058a027
--- /dev/null
+++ b/scripts/training/zhizhi_v2/ds_config.json
@@ -0,0 +1,56 @@
+{
+  "train_batch_size": "auto",
+  "train_micro_batch_size_per_gpu": 1,
+  "gradient_accumulation_steps": 8,
+  "optimizer": {
+    "type": "AdamW",
+    "params": {
+      "lr": 5e-6,
+      "betas": [0.9, 0.999],
+      "eps": 1e-8,
+      "weight_decay": 0.01
+    }
+  },
+  "scheduler": {
+    "type": "WarmupLR",
+    "params": {
+      "warmup_min_lr": 0,
+      "warmup_max_lr": 5e-6,
+      "warmup_num_steps": 100
+    }
+  },
+  "zero_optimization": {
+    "stage": 2,
+    "offload_optimizer": {
+      "device": "cpu",
+      "pin_memory": true
+    },
+    "allgather_partitions": true,
+    "allgather_bucket_size": 2e8,
+    "overlap_comm": true,
+    "reduce_scatter": true,
+    "reduce_bucket_size": 2e8,
+    "contiguous_gradients": true
+  },
+  "gradient_clipping": 1.0,
+  "fp16": {
+    "enabled": "auto",
+    "loss_scale": 0,
+    "loss_scale_window": 1000,
+    "initial_scale_power": 16,
+    "hysteresis": 2,
+    "min_loss_scale": 1
+  },
+  "bf16": {
+    "enabled": "auto"
+  },
+  "activation_checkpointing": {
+    "partition_activations": false,
+    "cpu_checkpointing": false,
+    "contiguous_memory_optimization": false,
+    "number_checkpoints": null,
+    "synchronize_checkpoint_boundary": false,
+    "profile": false
+  },
+  "wall_clock_breakdown": false
+}