metadata
library_name: peft
tags:
- open-llama
- llama
- code
- instruct
- instruct-code
- code-alpaca
- alpaca-instruct
- alpaca
- llama7b
datasets:
- ewof/code-alpaca-instruct-unfiltered
base_model: openlm-research/open_llama_7b
We finetuned Open Llama 7B on Code-Alpaca-Instruct Dataset (ewof/code-alpaca-instruct-unfiltered) for 3 epochs using MonsterAPI no-code LLM finetuner.
This dataset is HuggingFaceH4/CodeAlpaca_20K unfiltered, removing 36 instances of blatant alignment.
The finetuning session got completed in 75 minutes and costed us only $3 for the entire finetuning run!
Loss metrics:
