Hopiu/llm
1
0
Fork 0
mirror of https://github.com/Hopiu/llm.git synced 2026-04-10 00:10:58 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

o1-preview and o1-mini, refs #570 (#573)

Browse source
This commit is contained in:
Simon Willison 2024-09-12 16:08:04 -07:00 committed by GitHub
parent 50520c7c1c
commit bfcfd2c91b
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 31 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
docs/openai-models.md
View file

@ -41,6 +41,8 @@ OpenAI Chat: gpt-4-turbo-2024-04-09
OpenAI Chat: gpt-4-turbo (aliases: gpt-4-turbo-preview, 4-turbo, 4t)
OpenAI Chat: gpt-4o (aliases: 4o)
OpenAI Chat: gpt-4o-mini (aliases: 4o-mini)
OpenAI Chat: o1-preview
OpenAI Chat: o1-mini
OpenAI Completion: gpt-3.5-turbo-instruct (aliases: 3.5-instruct, chatgpt-instruct)
```
<!-- [[[end]]] -->

20
docs/usage.md
View file

@ -345,6 +345,26 @@ OpenAI Chat: gpt-4o-mini (aliases: 4o-mini)
logit_bias: dict, str
seed: int
json_object: boolean
OpenAI Chat: o1-preview
temperature: float
max_tokens: int
top_p: float
frequency_penalty: float
presence_penalty: float
stop: str
logit_bias: dict, str
seed: int
json_object: boolean
OpenAI Chat: o1-mini
temperature: float
max_tokens: int
top_p: float
frequency_penalty: float
presence_penalty: float
stop: str
logit_bias: dict, str
seed: int
json_object: boolean
OpenAI Completion: gpt-3.5-turbo-instruct (aliases: 3.5-instruct, chatgpt-instruct)
temperature: float
What sampling temperature to use, between 0 and 2. Higher values like

10
llm/default_plugins/openai_models.py
View file

@ -35,6 +35,9 @@ def register_models(register):
# GPT-4o
register(Chat("gpt-4o"), aliases=("4o",))
register(Chat("gpt-4o-mini"), aliases=("4o-mini",))
# o1
register(Chat("o1-preview", can_stream=False, allows_system_prompt=False))
register(Chat("o1-mini", can_stream=False, allows_system_prompt=False))
# The -instruct completion model
register(
Completion("gpt-3.5-turbo-instruct", default_max_tokens=256),
@ -248,7 +251,6 @@ class SharedOptions(llm.Options):
class Chat(Model):
needs_key = "openai"
key_env_var = "OPENAI_API_KEY"
can_stream: bool = True
default_max_tokens = None
@ -268,6 +270,8 @@ class Chat(Model):
api_version=None,
api_engine=None,
headers=None,
can_stream=True,
allows_system_prompt=True,
):
self.model_id = model_id
self.key = key
@ -277,12 +281,16 @@ class Chat(Model):
self.api_version = api_version
self.api_engine = api_engine
self.headers = headers
self.can_stream = can_stream
self.allows_system_prompt = allows_system_prompt
def __str__(self):
return "OpenAI Chat: {}".format(self.model_id)
def execute(self, prompt, stream, response, conversation=None):
messages = []
if prompt.system and not self.allows_system_prompt:
raise NotImplementedError("Model does not support system prompts")
current_system = None
if conversation is not None:
for prev_response in conversation.responses: