Discord-Hermes-3-8B

Model Description

This is a fine-tuned version of NousResearch/Hermes-3-Llama-3.1-8B, trained on a curated dataset built from a mixture of enhanced and original samples from mookiezi/Discord-Dialogues.

The training hyper-parameters and log are available here.

---

Sample Outputs

⚠️ Disclaimer: The first image is fictional dialogue.
It should not be interpreted as political advice, a statement of fact, or an endorsement of any kind.

---

Interfacing

An optimized Python script for interfacing is available here.

Windows

py interface.py

macOS

python3 interface.py

Linux

python3 interface.py

​ ​ ​