Zero Loss ! from 4-Bit Conversion ! ---- I Use these models for Finetuning ! or even downloading local on home machine , enabling executing on laptop ! ------ Hence I train In 4bit! Qlora !

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

Safetensors

Model size

3.86B params

Tensor type

F32

BF16

Inference Examples

Inference API (serverless) is not available, repository is disabled.

Model tree for LeroyDyer/_Spydaz_Web_AI_ChatQA_001_4_BIT

Base model

Quantized

this model