base_model, language, license, tags, datasets

base_model	language	license	tags	datasets
unsloth/meta-llama-3.1-8b-bnb-4bit	en	apache-2.0	text-generation-inference transformers unsloth llama trl sft cleverboi theprint	iamtarun/python_code_instructions_18k_alpaca

CleverBoi

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.

Uploaded model

• Developed by: theprint
• License: apache-2.0
• Finetuned from model : unsloth/meta-llama-3.1-8b-bnb-4bit

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.