Improved token counting for OpenAI endpoints (llama.cpp token count -> cached prompt_tokens from last output -> naive string estimate). Logger refactoring with JSON format debugging to log file. Various bugfixes. Removed unused templates.py
This commit is contained in:
@@ -0,0 +1,2 @@
|
||||
requests>=2.28.0
|
||||
rich>=13.0.0
|
||||
Reference in New Issue
Block a user