AI/gpt4all
1
0
Fork 0
mirror of https://github.com/nomic-ai/gpt4all.git synced 2024-10-01 01:06:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

add fake_reply parameter to Embed4All.generate()

Browse Source
This commit is contained in:
adbenitez 2024-09-04 18:05:58 +02:00
parent e48571003e
commit 34d204b5e3
2 changed files with 5 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
gpt4all-bindings/python/gpt4all/_pyllmodel.py
View File

@ -493,6 +493,7 @@ class LLModel:
context_erase: float = 0.75,
reset_context: bool = False,
special: bool = False,
fake_reply: str = "",
):
"""
Generate response from model from a prompt.
@ -537,7 +538,7 @@ class LLModel:
True,
self.context,
special,
ctypes.c_char_p(),
ctypes.c_char_p(fake_reply.encode()) if fake_reply else ctypes.c_char_p(),
)

3
gpt4all-bindings/python/gpt4all/gpt4all.py
View File

@ -496,6 +496,7 @@ class GPT4All:
n_batch: int = 8,
n_predict: int | None = None,
streaming: bool = False,
fake_reply: str = "",
callback: ResponseCallbackType = empty_response_callback,
) -> Any:
"""
@ -513,6 +514,7 @@ class GPT4All:
n_batch: Number of prompt tokens processed in parallel. Larger values decrease latency but increase resource requirements.
n_predict: Equivalent to max_tokens, exists for backwards compatibility.
streaming: If True, this method will instead return a generator that yields tokens as the model generates them.
fake_reply: A spoofed reply for the given prompt, used as a way to load chat history.
callback: A function with arguments token_id:int and response:str, which receives the tokens from the model as they are generated and stops the generation by returning False.
Returns:
@ -529,6 +531,7 @@ class GPT4All:
repeat_last_n=repeat_last_n,
n_batch=n_batch,
n_predict=n_predict if n_predict is not None else max_tokens,
fake_reply=fake_reply,
)
if self._history is not None: