theprint's picture
Update README.md
8ac5ed7 verified
metadata
base_model: unsloth/gemma-3-12b-it-unsloth-bnb-4bit
tags:
  - text-generation-inference
  - transformers
  - unsloth
  - gemma3
  - hemispheres
  - theprint
license: apache-2.0
language:
  - en
datasets:
  - theprint/Hemispheres-v0.3-Combo-GPT

Trained on synthesis

The TextSynth series was fine tuned on the Hemispheres v0.3 Combo data set, which focuses on synthesizing text from two different sources. As such, this model is good at doing just that, summarization and similar text-related tasks.

Uploaded finetuned model

  • Developed by: theprint
  • License: apache-2.0
  • Finetuned from model : unsloth/gemma-3-12b-it-unsloth-bnb-4bit

This gemma3 model was trained 2x faster with Unsloth and Huggingface's TRL library.