PyPI page
Home page
Author:
Mervin Praison
Summary:
Training for PraisonAI — LLM fine-tuning (Unsloth) and iterative agent training extracted from the praisonai wrapper.
Latest version:
0.1.12
Required dependencies:
click
|
litellm
|
praisonaiagents
|
pyyaml
|
rich
|
typer
Optional dependencies:
accelerate
|
bitsandbytes
|
datasets
|
hf-transfer
|
huggingface-hub
|
peft
|
praisonai
|
praisonai-code
|
praisonai-train
|
protobuf
|
sentencepiece
|
torch
|
transformers
|
trl
|
unsloth
Downloads last day:
135
Downloads last week:
614
Downloads last month:
3,089
7-day smoothing