zuli12
zuli12
Thanks @nerder ! I do already have litellm installed on a never version: ``` ❯ pip list | grep litellm litellm 1.43.9 ❯ pip list | grep shell_gpt shell_gpt 1.4.4...
okay so the issue with the log message: > LiteLLM:WARNING: litellm_logging.py:1302 - Model=gemma2:2b not found in completion cost map. Setting 'response_cost' to None comes from litelllm not having the exact...
oh so sad, i love that model, time for their coding plan :)
actually pretty good idea, i would like that. Not checked the src, but the idea itself is great! kudos, hope this or something similar get's imported / implemented! 👍