Thanks to visit codestin.com Credit goes to github.com
We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent 8432116 commit e966f3bCopy full SHA for e966f3b
llama_cpp/llama.py
@@ -777,11 +777,12 @@ def generate(
777
else:
778
break
779
if longest_prefix > 0:
780
- if self.verbose:
781
- print("Llama.generate: prefix-match hit", file=sys.stderr)
782
reset = False
783
tokens = tokens[longest_prefix:]
784
self.n_tokens = longest_prefix
+ if self.verbose:
+ print(f"Llama.generate: {longest_prefix} prefix-match hit, "
785
+ f"remaining {len(tokens)} prompt tokens to eval", file=sys.stderr)
786
787
# Reset the model state
788
if reset:
0 commit comments