This is an experimental fine tune of
theprint/CleverBoi-Llama-3.1-8B-v2, which was given additional fine tuning on the
iamtarun/python_code_instructions_18k_alpaca data set (1 epoch).
The CleverBoi series is based on models that have been fine tuned on a collection of data sets that emphasize logic, inference, math and coding, also known as the CleverBoi data set.
This llama model was trained 2x faster with
Unsloth and Huggingface's TRL library.
