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: 22

Safetensors

Model size

7.24B params

Tensor type

FP16

Inference Examples

Text Generation

This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for davanstrien/HaikuHermes-0.1-7B

Base model

mistralai/Mistral-7B-v0.1

Finetuned

teknium/OpenHermes-2.5-Mistral-7B

Finetuned

(71)

this model

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

Collection including davanstrien/HaikuHermes-0.1-7B

haiku

Collection

🌸 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 Jun 21 • 6