Merge branch 'main' into feat/support_ms

Former-commit-id: 698756dffb7d4e602b3e0cab66ef0a4befe7215c

src/llmtuner/hparams/data_args.py

@@ -17,6 +17,7 @@ class DatasetAttr:
     dataset_sha1: Optional[str] = None
     system_prompt: Optional[str] = None
     subset: Optional[str] = None
+    folder: Optional[str] = None
     ranking: Optional[bool] = False
     formatting: Optional[Literal["alpaca", "sharegpt"]] = "alpaca"
 
@@ -184,6 +185,7 @@ class DataArguments:
                 dataset_attr.content = dataset_info[name]["columns"].get("content", None)
 
             dataset_attr.subset = dataset_info[name].get("subset", None)
+            dataset_attr.folder = dataset_info[name].get("folder", None)
             dataset_attr.ranking = dataset_info[name].get("ranking", False)
             dataset_attr.formatting = dataset_info[name].get("formatting", "alpaca")
             dataset_attr.system_prompt = prompt_list[i]

src/llmtuner/hparams/finetuning_args.py

@@ -118,9 +118,9 @@ class RLHFArguments:
         default=None,
         metadata={"help": "The number of bits to quantize the reward model."}
     )
-    reward_model_type: Optional[Literal["lora", "full"]] = field(
+    reward_model_type: Optional[Literal["lora", "full", "api"]] = field(
         default="lora",
-        metadata={"help": "The checkpoint type of the reward model. The lora type only supports lora training."}
+        metadata={"help": "The type of the reward model in PPO training. Lora model only supports lora training."}
     )
 
 
@@ -141,10 +141,6 @@ class FinetuningArguments(FreezeArguments, LoraArguments, RLHFArguments):
         default=False,
         metadata={"help": "Whether to upcast the layernorm weights in fp32."}
     )
-    neft_alpha: Optional[float] = field(
-        default=0,
-        metadata={"help": "The alpha parameter to control the noise magnitude in NEFTune."}
-    )
     export_dir: Optional[str] = field(
         default=None,
         metadata={"help": "Path to the directory to save the exported model."}

src/llmtuner/hparams/model_args.py

@@ -8,8 +8,8 @@ class ModelArguments:
     Arguments pertaining to which model/config/tokenizer we are going to fine-tune.
     """
     model_name_or_path: str = field(
-        metadata={"help": "Path to pretrained model or model identifier "
-                          "from huggingface.co/models or modelscope.cn/models."}
+        metadata={"help": "Path to pretrained model or model identifier from \
+                  huggingface.co/models or modelscope.cn/models."}
     )
     cache_dir: Optional[str] = field(
         default=None,