dfurman
/

Llama-2-70B-Instruct-v0.1

Text Generation

Model card Files Files and versions

dfurman commited on Jul 27, 2023

Commit

a1190de

·

1 Parent(s): f5d8516

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -195,7 +195,7 @@ def llama_generate(
     tokenizer: AutoTokenizer,
     prompt: str,
     max_new_tokens: int = 128,
-    temperature: int = 1.0,
 ) -> str:
     """
     Initialize the pipeline

     tokenizer: AutoTokenizer,
     prompt: str,
     max_new_tokens: int = 128,
+    temperature: float = 0.92,
 ) -> str:
     """
     Initialize the pipeline