mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-12-25 02:44:36 +00:00
change default temperature of OAI compat API from 0 to 1 (#7226)
* change default temperature of OAI compat API from 0 to 1 * make tests explicitly send temperature to OAI API
This commit is contained in:
parent
cbf75894d2
commit
e586ee4259
@ -887,6 +887,7 @@ async def oai_chat_completions(user_prompt,
|
|||||||
base_path,
|
base_path,
|
||||||
async_client,
|
async_client,
|
||||||
debug=False,
|
debug=False,
|
||||||
|
temperature=None,
|
||||||
model=None,
|
model=None,
|
||||||
n_predict=None,
|
n_predict=None,
|
||||||
enable_streaming=None,
|
enable_streaming=None,
|
||||||
@ -913,7 +914,8 @@ async def oai_chat_completions(user_prompt,
|
|||||||
"model": model,
|
"model": model,
|
||||||
"max_tokens": n_predict,
|
"max_tokens": n_predict,
|
||||||
"stream": enable_streaming,
|
"stream": enable_streaming,
|
||||||
"seed": seed
|
"temperature": temperature if temperature is not None else 0.0,
|
||||||
|
"seed": seed,
|
||||||
}
|
}
|
||||||
if response_format is not None:
|
if response_format is not None:
|
||||||
payload['response_format'] = response_format
|
payload['response_format'] = response_format
|
||||||
@ -978,7 +980,8 @@ async def oai_chat_completions(user_prompt,
|
|||||||
max_tokens=n_predict,
|
max_tokens=n_predict,
|
||||||
stream=enable_streaming,
|
stream=enable_streaming,
|
||||||
response_format=payload.get('response_format'),
|
response_format=payload.get('response_format'),
|
||||||
seed=seed
|
seed=seed,
|
||||||
|
temperature=payload['temperature']
|
||||||
)
|
)
|
||||||
except openai.error.AuthenticationError as e:
|
except openai.error.AuthenticationError as e:
|
||||||
if expect_api_error is not None and expect_api_error:
|
if expect_api_error is not None and expect_api_error:
|
||||||
|
@ -371,7 +371,7 @@ static json oaicompat_completion_params_parse(
|
|||||||
llama_params["presence_penalty"] = json_value(body, "presence_penalty", 0.0);
|
llama_params["presence_penalty"] = json_value(body, "presence_penalty", 0.0);
|
||||||
llama_params["seed"] = json_value(body, "seed", LLAMA_DEFAULT_SEED);
|
llama_params["seed"] = json_value(body, "seed", LLAMA_DEFAULT_SEED);
|
||||||
llama_params["stream"] = json_value(body, "stream", false);
|
llama_params["stream"] = json_value(body, "stream", false);
|
||||||
llama_params["temperature"] = json_value(body, "temperature", 0.0);
|
llama_params["temperature"] = json_value(body, "temperature", 1.0);
|
||||||
llama_params["top_p"] = json_value(body, "top_p", 1.0);
|
llama_params["top_p"] = json_value(body, "top_p", 1.0);
|
||||||
|
|
||||||
// Apply chat template to the list of messages
|
// Apply chat template to the list of messages
|
||||||
|
Loading…
Reference in New Issue
Block a user