|
|
--- |
|
|
license: apache-2.0 |
|
|
tags: |
|
|
- merge |
|
|
- mergekit |
|
|
- lazymergekit |
|
|
- finetuned |
|
|
- mistralai/Mistral-7B-Instruct-v0.2 |
|
|
- janai-hq/trinity-v1 |
|
|
- wenqiglantz/MistralTrinity-7b-slerp |
|
|
--- |
|
|
|
|
|
# MistralTrinity-7B-slerp-finetuned |
|
|
|
|
|
MistralTrinity-7B-slerp-finetuned is a fine-tuned model of [MistralTrinity-7B-slerp](https://huggingface.co/wenqiglantz/MistralTrinity-7B-slerp), which was merged from the following two models using [mergekit](https://github.com/cg123/mergekit): |
|
|
* [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) |
|
|
* [janai-hq/trinity-v1](https://huggingface.co/janai-hq/trinity-v1) |
|
|
|
|
|
## Dataset |
|
|
|
|
|
The dataset used for fine-tuning is from [wenqiglantz/guanaco-llama2-2k](https://huggingface.co/datasets/wenqiglantz/guanaco-llama2-2k), a subset (2000 samples) of [timdettmers/openassistant-guanaco](https://huggingface.co/datasets/timdettmers/openassistant-guanaco) dataset. |
|
|
|
|
|
|
