root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-24 10:24:35 +00:00
Code Issues Actions 5 Packages Projects Releases Wiki Activity

change default temperature of OAI compat API from 0 to 1 (#7226)

Browse Source 
* change default temperature of OAI compat API from 0 to 1

* make tests explicitly send temperature to OAI API
This commit is contained in:
Benjamin Findley 2024-05-12 19:40:08 -07:00 committed by GitHub
parent cbf75894d2
commit e586ee4259
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 6 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
examples/server/tests/features/steps/steps.py
View File

@ -887,6 +887,7 @@ async def oai_chat_completions(user_prompt,
base_path,
async_client,
debug=False,
temperature=None,
model=None,
n_predict=None,
enable_streaming=None,
@ -913,7 +914,8 @@ async def oai_chat_completions(user_prompt,
"model": model,
"max_tokens": n_predict,
"stream": enable_streaming,
"seed": seed
"temperature": temperature if temperature is not None else 0.0,
"seed": seed,
}
if response_format is not None:
payload['response_format'] = response_format
@ -978,7 +980,8 @@ async def oai_chat_completions(user_prompt,
max_tokens=n_predict,
stream=enable_streaming,
response_format=payload.get('response_format'),
seed=seed
seed=seed,
temperature=payload['temperature']
)
except openai.error.AuthenticationError as e:
if expect_api_error is not None and expect_api_error:

2
examples/server/utils.hpp
View File

@ -371,7 +371,7 @@ static json oaicompat_completion_params_parse(
llama_params["presence_penalty"] = json_value(body, "presence_penalty", 0.0);
llama_params["seed"] = json_value(body, "seed", LLAMA_DEFAULT_SEED);
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);
// Apply chat template to the list of messages