---
license: wtfpl
datasets:
- teknium/openhermes
pipeline_tag: text-generation
thumbnail: https://huggingface.co/mrm8488/stablelm2-1.6b-ft-openhermes/resolve/main/logo.png
language:
- en
---

# **S**tablelm2- (1.6b) fine-tuned on OpenHermes

<div style="text-align:center;">
    <img src="https://huggingface.co/mrm8488/stablelm2-1.6b-ft-openhermes/resolve/main/logo.png" alt="logo" style="width:150px; height:200px;">
</div>



## Base model info

`Stable LM 2 1.6B` is a 1.6 billion parameter decoder-only language model pre-trained on 2 trillion tokens of diverse multilingual and code datasets for two epochs.

## Dataset info

The OpenHermes dataset is composed of 242,000 entries of primarily GPT-4 generated data from open datasets across the AI landscape, including:

OpenHermes 13B is the first fine tune of the Hermes dataset that has a fully open source dataset!

OpenHermes was trained on 242,000 entries of primarily GPT-4 generated data from open datasets across the AI landscape, including:

- GPTeacher - General Instruct, Roleplay v1, Roleplay v2, and Code Instruct Datasets, by Teknium
- WizardLM (v1, evol_instruct 70k), by WizardLM Team/nlpxucan
- Airoboros GPT-4 (v1.0), by JonDurbin
- Camel-AI's domain expert datasets, by the Camel-AI Team
- CodeAlpaca, by Sahil2801
- GPT4-LLM and Unnatural Instructions, by Microsoft
Filtering included the removal of OpenAI refusals, disclaimers, and "As an AI" type examples and more
The base dataset mix is identical to the original Nous-Hermes', minus the Nous-Instruct and PDACTL datasets which were private datasets.

## Usage

WIP


## Evaluations

WIP