初始化项目，由ModelHub XC社区提供模型

Model: fungamer2/Ami-360M-Thinking
Source: Original Platform

training_params.json

@@ -0,0 +1,49 @@
+{
+    "model": "fungamer2/Ami-360M-Thinking-SFT-Test1",
+    "project_name": "Ami-360M-Thinking-DPO-Test2-2",
+    "data_path": "Ami-360M-Thinking-DPO-Test2-2/autotrain-data",
+    "train_split": "train",
+    "valid_split": null,
+    "add_eos_token": true,
+    "block_size": 1024,
+    "model_max_length": 10240,
+    "padding": "right",
+    "trainer": "dpo",
+    "use_flash_attention_2": false,
+    "log": "tensorboard",
+    "disable_gradient_checkpointing": false,
+    "logging_steps": -1,
+    "eval_strategy": "epoch",
+    "save_total_limit": 1,
+    "auto_find_batch_size": false,
+    "mixed_precision": "none",
+    "lr": 1e-06,
+    "epochs": 2,
+    "batch_size": 1,
+    "warmup_ratio": 0.1,
+    "gradient_accumulation": 3,
+    "optimizer": "adamw_torch",
+    "scheduler": "linear",
+    "weight_decay": 0.0,
+    "max_grad_norm": 1.0,
+    "seed": 42,
+    "chat_template": "tokenizer",
+    "quantization": "int4",
+    "target_modules": "all-linear",
+    "merge_adapter": false,
+    "peft": false,
+    "lora_r": 16,
+    "lora_alpha": 32,
+    "lora_dropout": 0.05,
+    "model_ref": null,
+    "dpo_beta": 0.1,
+    "max_prompt_length": 768,
+    "max_completion_length": null,
+    "prompt_text_column": "autotrain_prompt",
+    "text_column": "autotrain_text",
+    "rejected_text_column": "autotrain_rejected_text",
+    "push_to_hub": true,
+    "username": "fungamer2",
+    "unsloth": false,
+    "distributed_backend": "deepspeed"
+}