CoolFace
Modelpublic

penguin-wall/hydra_chastity

sourceHugging Facemitupdated 1y agoView on Hugging Face
1likes87downloads
Model Card

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.

<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>