---
base_model:
- mistralai/Mistral-7B-Instruct-v0.1

library_name: transformers
tags:
- mergekit
- merge
license: mit
language:
- en
metrics:
- code_eval
- accuracy
- bleu
---
# Mixtral_Chat_7b

This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).

## Merge Details
### Merge Method

This model was merged using the [linear](https://arxiv.org/abs/2203.05482) merge method.

### Models Merged

The following models were included in the merge:

  Locutusque/Hercules-3.1-Mistral-7B:
-Contains erronious
  mistralai/Mistral-7B-Instruct-v0.2:
-contains the eronous model !
  NousResearch/Hermes-2-Pro-Mistral-7B:
  -Good


### Configuration

The following YAML configuration was used to produce this model:

```yaml

models:
  - model: LeroyDyer/Mixtral_Base_Chat_7b
    parameters:
      weight: 0.7
  - model: LeroyDyer/Mixtral_Base_Chat_7b_2.0
    parameters:
      weight: 0.3
merge_method: linear
dtype: float16

```