README.md

---
base_model: mistralai/Mistral-7B-v0.1
tags:
- mistral-7b
- instruct
- finetune
- gpt4
- synthetic data
- distillation
model-index:
- name: Mistral-Trismegistus-7B
  results: []
license: apache-2.0
language:
- en
---
**Mistral Trismegistus 7B**

<div style="display: flex; justify-content: center;">
  <img src="https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/3VJvztFDB1XOWfShuHnb6.png" alt="Mistral Trismegistus" width="50%" style="display: block; margin: 0 auto;">
</div>

## Model Description:

Transcendence is All You Need! Mistral Trismegistus is a model made for people interested in the esoteric, occult, and spiritual. 

Here are some outputs:

Answer questions about occult artifacts:
![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/WeLd-zbZVwRe6HjxyRYMh.png)

Play the role of a hypnotist:
![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/fdYQacOpD3GrLCdgCrMLu.png)


## Special Features:
- **The First Powerful Occult Expert Model**: ~10,000 high quality, deep, rich, instructions on the occult, esoteric, and spiritual.
- **Fast**: Trained on Mistral, a state of the art 7B parameter model, you can run this model FAST on even a cpu.
- **Not a positivity-nazi**: This model was trained on all forms of esoteric tasks and knowledge, and is not burdened by the flowery nature of many other models, who chose positivity over creativity.

## Acknowledgements:

Special thanks to @a16z.

## Dataset:

This model was trained on a 100% synthetic, gpt-4 generated dataset, about ~10,000 examples, on a wide and diverse set of both tasks and knowledge about the esoteric, occult, and spiritual.

The dataset will be released soon!

## Usage:

Prompt Format:
```
USER: <prompt>
ASSISTANT:
```
OR
```
<system message>
USER: <prompt>
ASSISTANT:
```

## Benchmarks:

No benchmark can capture the nature and essense of the quality of spirituality and esoteric knowledge and tasks. You will have to try testing it yourself!

Training run on wandb here: https://wandb.ai/teknium1/occult-expert-mistral-7b/runs/coccult-expert-mistral-6/overview

## Licensing:

Apache 2.0

---


# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_teknium__Mistral-Trismegistus-7B)

| Metric                | Value                     |
|-----------------------|---------------------------|
| Avg.                  | 46.17   |
| ARC (25-shot)         | 54.1          |
| HellaSwag (10-shot)   | 77.91    |
| MMLU (5-shot)         | 54.49         |
| TruthfulQA (0-shot)   | 49.36   |
| Winogrande (5-shot)   | 70.17   |
| GSM8K (5-shot)        | 9.93        |
| DROP (3-shot)         | 7.24         |