base_model: unsloth/meta-llama-3.1-8b-instruct-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
license: apache-2.0
language:
- en
NightPrompt AI RV1 ( Instruction-Response Support)
Welcome 😊, This is the official HuggingFace repository for the first version of NightPrompt AI. It is fine-tuned under LLama 3.2 using unsloth. This model is fine-tuned using the https://huggingface.co/datasets/Afifsudoers/NightPrompt-V1-Alpha-Dataset-validation dataset.(52% of it was trained). This dataset consists of Coding, Alpaca prompt response converstion, Math-500,AIME and IMO math problems.
Estimated Accuracy(Testing Dataset )
91.5%
Average Loss Rate
0.43
EXTRA INFO COMING SOON
Messages From The Developer
I (Afif Ali Saadman), is the main mastermind behind this AI. This is my first-ever AI model released in HuggingFace. I wanna mention that I have made many models before, some were based on books, some were based on gibberish texts from the internet. And, this is my first time making and fine-tuning a full instruct based model. Though, some errors are inskippable. They will be fixed on the Alpha/Beta release. I had a target of making AI free and open source to everyone.
Uploaded model
- Developed by: Afifsudoers
- License: apache-2.0
- Finetuned from model : unsloth/meta-llama-3.1-8b-instruct-bnb-4bit
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.
