baalajimaestro/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

llama_cpp server: document presence_penalty and frequency_penalty, mark as supported

Browse source
This commit is contained in:
Lucas Doyle 2023-05-09 16:19:46 -07:00
parent d957422bf4
commit 02e8a018ae
1 changed files with 17 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

21
llama_cpp/server/app.py
View file

@ -152,6 +152,19 @@ repeat_penalty_field = Field(
+ "Repeat penalty is a hyperparameter used to penalize the repetition of token sequences during text generation. It helps prevent the model from generating repetitive or monotonous text. A higher value (e.g., 1.5) will penalize repetitions more strongly, while a lower value (e.g., 0.9) will be more lenient.", + "Repeat penalty is a hyperparameter used to penalize the repetition of token sequences during text generation. It helps prevent the model from generating repetitive or monotonous text. A higher value (e.g., 1.5) will penalize repetitions more strongly, while a lower value (e.g., 0.9) will be more lenient.",
) )
presence_penalty_field = Field(
default=0.0,
ge=-2.0,
le=2.0,
description="Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.",
)
frequency_penalty_field = Field(
default=0.0,
ge=-2.0,
le=2.0,
description="Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.",
)
class CreateCompletionRequest(BaseModel): class CreateCompletionRequest(BaseModel):
prompt: Optional[str] = Field( prompt: Optional[str] = Field(
@ -175,13 +188,13 @@ class CreateCompletionRequest(BaseModel):
ge=0, ge=0,
description="The number of logprobs to generate. If None, no logprobs are generated.", description="The number of logprobs to generate. If None, no logprobs are generated.",
) )
presence_penalty: Optional[float] = presence_penalty_field
frequency_penalty: Optional[float] = frequency_penalty_field
# ignored or currently unsupported # ignored or currently unsupported
model: Optional[str] = model_field model: Optional[str] = model_field
n: Optional[int] = 1 n: Optional[int] = 1
logprobs: Optional[int] = Field(None) logprobs: Optional[int] = Field(None)
presence_penalty: Optional[float] = 0
frequency_penalty: Optional[float] = 0
best_of: Optional[int] = 1 best_of: Optional[int] = 1
logit_bias: Optional[Dict[str, float]] = Field(None) logit_bias: Optional[Dict[str, float]] = Field(None)
user: Optional[str] = Field(None) user: Optional[str] = Field(None)
@ -269,12 +282,12 @@ class CreateChatCompletionRequest(BaseModel):
top_p: float = top_p_field top_p: float = top_p_field
stop: Optional[List[str]] = stop_field stop: Optional[List[str]] = stop_field
stream: bool = stream_field stream: bool = stream_field
presence_penalty: Optional[float] = presence_penalty_field
frequency_penalty: Optional[float] = frequency_penalty_field
# ignored or currently unsupported # ignored or currently unsupported
model: Optional[str] = model_field model: Optional[str] = model_field
n: Optional[int] = 1 n: Optional[int] = 1
presence_penalty: Optional[float] = 0
frequency_penalty: Optional[float] = 0
logit_bias: Optional[Dict[str, float]] = Field(None) logit_bias: Optional[Dict[str, float]] = Field(None)
user: Optional[str] = Field(None) user: Optional[str] = Field(None)