Issues
- 8
- 2
llm hangs forever when running Replicate models
#24 opened by zeke - 2
"llama_cpp not installed" even after I install it
#21 opened by zeke - 3
TypeError: 'NoneType' object is not subscriptable
#22 opened by zeke - 1
- 1
KeyError: 'id' in version 0.2
#18 opened by thiswillbeyourgithub - 0
--system flag seems to be ignored
#17 opened by 0xalpharush - 0
- 1
Feature request: log the prediction time
#14 opened by jamesscottbrown - 0
Fine tuning of llama2
#13 opened by harlantwood - 10
- 2
- 1
- 2
Support for chat models and conversations
#8 opened by simonw - 5
Add support for options
#4 opened by simonw - 2
Vendor replicate-python and ship to PyPI
#3 opened by simonw - 5
Ability to register extra models
#2 opened by simonw - 8
Initial plugin
#1 opened by simonw