Half the data was geared towards better reasoning (EvolKit-20k and reasoning-base-20k), the other half will help to de-censor the model (WizardLM data set).

Uploaded model

Developed by: theprint
License: apache-2.0
Finetuned from model : theprint/ReWiz-Worldbuilder-7B

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

Downloads last month: 41

GGUF

Model size

7.25B params

Architecture

llama

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for theprint/ReWiz-Worldbuilder-7B-GGUF

Base model

theprint/ReWiz-Worldbuilder-7B

Quantized

(3)

this model

Collection including theprint/ReWiz-Worldbuilder-7B-GGUF

ReWiz

Collection

The ReWiz series is based on a subset of data from 3 different data sets, which has been used for fine tuning. • 16 items • Updated 3 days ago • 1