github/gpt4all
1
0
Fork 0
mirror of https://github.com/nomic-ai/gpt4all.git synced 2025-06-25 23:13:06 +00:00
Code Issues Packages Projects Releases Wiki Activity

bindings/python: fix typo (#1111)

Browse Source
This commit is contained in:
Aaron Miller 2023-06-30 14:00:42 -07:00 committed by GitHub
parent 46a0762bd5
commit ac5c8e964f
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
gpt4all-bindings/python/gpt4all/gpt4all.py
View File

@ -196,7 +196,7 @@ class GPT4All:
repeat_penalty: Penalize the model for repetition. Higher values result in less repetition. repeat_penalty: Penalize the model for repetition. Higher values result in less repetition.
repeat_last_n: How far in the models generation history to apply the repeat penalty. repeat_last_n: How far in the models generation history to apply the repeat penalty.
n_batch: Number of prompt tokens processed in parallel. Larger values decrease latency but increase resource requirements. 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 compatability. 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. streaming: If True, this method will instead return a generator that yields tokens as the model generates them.
Returns: Returns: