davanstrien
/

HaikuHermes-0.1-7B

Text Generation

Inference Endpoints

text-generation-inference

Model card Files Files and versions Community

Edit model card

Model Card for HaikuHermes-0.1-7B

This is a very early model which uses the davanstrien/haiku_dpo dataset to train teknium/OpenHermes-2.5-Mistral-7B using Direct Preference Optimization.

The eventual goal of this model is for it to write "technically correct" haiku.

Downloads last month: 1

Safetensors

Model size

7.24B params

Tensor type

FP16

·

Finetuned from

Dataset used to train davanstrien/HaikuHermes-0.1-7B

Collection including davanstrien/HaikuHermes-0.1-7B

haiku

🌸 This is a collection of synthetic datasets built to help improve the ability of open language models to better write haikus through the use of DPO • 3 items • Updated 8 days ago • 4