support vllm

Former-commit-id: 889f6e910e654d8ec3922c2185042d737ffbf1c3

src/llmtuner/hparams/generating_args.py

@@ -1,5 +1,5 @@
 from dataclasses import asdict, dataclass, field
-from typing import Any, Dict, Optional
+from typing import Any, Dict
 
 
 @dataclass
@@ -8,41 +8,41 @@ class GeneratingArguments:
     Arguments pertaining to specify the decoding parameters.
     """
 
-    do_sample: Optional[bool] = field(
+    do_sample: bool = field(
         default=True,
         metadata={"help": "Whether or not to use sampling, use greedy decoding otherwise."},
     )
-    temperature: Optional[float] = field(
+    temperature: float = field(
         default=0.95,
         metadata={"help": "The value used to modulate the next token probabilities."},
     )
-    top_p: Optional[float] = field(
+    top_p: float = field(
         default=0.7,
         metadata={
             "help": "The smallest set of most probable tokens with probabilities that add up to top_p or higher are kept."
         },
     )
-    top_k: Optional[int] = field(
+    top_k: int = field(
         default=50,
         metadata={"help": "The number of highest probability vocabulary tokens to keep for top-k filtering."},
     )
-    num_beams: Optional[int] = field(
+    num_beams: int = field(
         default=1,
         metadata={"help": "Number of beams for beam search. 1 means no beam search."},
     )
-    max_length: Optional[int] = field(
+    max_length: int = field(
         default=512,
         metadata={"help": "The maximum length the generated tokens can have. It can be overridden by max_new_tokens."},
     )
-    max_new_tokens: Optional[int] = field(
+    max_new_tokens: int = field(
         default=512,
         metadata={"help": "The maximum numbers of tokens to generate, ignoring the number of tokens in the prompt."},
     )
-    repetition_penalty: Optional[float] = field(
+    repetition_penalty: float = field(
         default=1.0,
         metadata={"help": "The parameter for repetition penalty. 1.0 means no penalty."},
     )
-    length_penalty: Optional[float] = field(
+    length_penalty: float = field(
         default=1.0,
         metadata={"help": "Exponential penalty to the length that is used with beam-based generation."},
     )