metadata
library_name: peft
license: apache-2.0
datasets:
- neuralwork/fashion-style-instruct
language:
- en
Style-Instruct Mistral 7B
Mistral 7B instruct fine-tuned on the neuralwork/fashion-style-instruct dataset with LoRA and 4bit quantization. See the blog post and Github repository for training details. This model is trained with body type / personal style descriptions as input, target events (e.g. casual date, business meeting) as context and outfit combination suggestions as output.
Usage
This repo contains the LoRA parameters of the fine-tuned Mistral 7B model. To perform inference, load and use the model as follows: