|
--- |
|
base_model: mistralai/Mistral-7B-v0.1 |
|
datasets: |
|
- gbstox/agronomy-resources |
|
tags: |
|
- mistral |
|
- instruct |
|
- finetune |
|
- agriculture |
|
language: |
|
- en |
|
--- |
|
|
|
# AgronoMistral |
|
<img src="https://cdn-uploads.huggingface.co/production/uploads/63042a3d7373aacccd896484/UqOsPoPc__ytlGDHYfI9S.jpeg" width="800" > |
|
|
|
# About |
|
Agronomistral is fine tuned with agronomy information from textbooks, university extension websites, government websites, and agronomic studies. |
|
<br>Agronomistral consistently outperforms the base model, mistralai/Mistral-7B-v0.1 on the [agronomy benchmark](https://github.com/gbstox/agronomy_llm_benchmarking). |
|
|
|
# Benchmark comparison |
|
| Model Name | Score | Date Tested | |
|
|----------------|-------|-----------------| |
|
| gpt-4-1106-preview | 83.84% | 2024-01-02 | |
|
| Mixtral-8x7B-Instruct-v0.1 | 75.76% | 2024-01-02 | |
|
| fbn-norm | 74.75% | 2024-01-02 | |
|
| gpt-3.5-turbo | 73.74% | 2024-01-02 | |
|
| OpenHermes-2p5-Mistral-7B | 65.66% | 2024-01-02 | |
|
| AgronoMistral | 58.59% | 2024-01-08 | |
|
| mistral-7b-instruct-v0.1_Q5_K_M | 47.47% | 2024-01-08 | |
|
|