alihan/llama-cpp-python
1
0
Fork 0
mirror of https://github.com/abetlen/llama-cpp-python.git synced 2023-09-07 17:34:22 +03:00
Code Issues Packages Projects Releases Wiki Activity

Fixed end of text wrong type, and fix n_predict behaviour

Browse Source
This commit is contained in:
Mug
2023-04-17 14:45:28 +02:00
parent 3bb45f1658
commit 53d17ad003
2 changed files with 7 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/low_level_api/common.py
View File

@@ -75,7 +75,7 @@ def gpt_params_parse(argv = None, params: Optional[GptParams] = None):
parser.add_argument("--top_p", type=float, default=0.95, help="top-p samplin",dest="top_p")
parser.add_argument("--top_k", type=int, default=40, help="top-k sampling",dest="top_k")
parser.add_argument("--temp", type=float, default=0.80, help="temperature",dest="temp")
parser.add_argument("--n_predict", type=int, default=128, help="number of model parts",dest="n_predict")
parser.add_argument("--n_predict", type=int, default=128, help="number of tokens to predict (-1 = infinity)",dest="n_predict")
parser.add_argument("--repeat_last_n", type=int, default=64, help="last n tokens to consider for penalize ",dest="repeat_last_n")
parser.add_argument("--repeat_penalty", type=float, default=1.10, help="penalize repeat sequence of tokens",dest="repeat_penalty")
parser.add_argument("-b", "--batch_size", type=int, default=8, help="batch size for prompt processing",dest="n_batch")