license: apache-2.0
base_model: mistralai/Mistral-7B-Instruct-v0.2
library_name: transformers
tags:
- mergekit
- merge
- mistral
- not-for-all-audiences
Model Card: ShoriRP-merged
This is a merge between:
- Mistral-7B-Instruct-v0.2
- ShoriRP at a weight of 1.00. The author uploads different versions, so the link goes to the author's page.
The merge was performed using mergekit.
The intended objective was to make a controlled test merge at a weight of 1.00
Branches
Since this is a test model, each version is located on a separate branch:
- v0.57: Version 0.57
- v0.60: Version 0.60
Configuration
The following YAML configuration was used to produce this model (x is the version of ShoriRP that's used):
merge_method: passthrough
models:
- model: F:\AI\models\Mistral-7B-Instruct-v0.2+F:\AI\loras\ShoriRP-vx
dtype: float16
Usage
Please see the Lora repository for proper usage. All the prompt formatting JSONs are included in this repo for your convenience.
Bias, Risks, and Limitations
The model will show biases similar to those observed in niche roleplaying forums on the Internet, besides those exhibited by the base model. It is not intended for supplying factual information or advice in any form.
Training Details
This model is merged and can be reproduced using the tools mentioned above. Please refer to all provided links for extra model-specific details.