penguin-wall/hydra_chastity
187
Hydra-Chastity-8B-FineTuned
- Developed by: penguin-wall
- License: MIT
- Finetuned from model : unsloth/meta-llama-3.1-8b-unsloth-bnb-4bit
Model Description
This model has been specialized to act as a friendly and expert forum member. Its primary function is to provide clear, helpful answers and examples within a forum context, while appropriately referencing topics and forum members by their usernames. Used a sample of training set scraped from various forum sites.
Hardware Usage during Training
- GPU: Tesla T4
- Max GPU Memory: 14.741 GB
- Memory Reserved (Initial): 6.881 GB
- Peak Reserved Memory (Total): 14.27 GB (96.805% of max memory)
- Peak Reserved Memory (for Training): 7.389 GB (50.126% of max memory)
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.
