Nexesenex/mrcuddle_Dark-Hermes3-Llama3.2-3B

Model Card

"Dark-Hermes3-Llama3.2-3B" is a fine-tuned version of NousResearch's Hermes 3B.

Original repo : https://huggingface.co/mrcuddle/Dark-Hermes3-Llama3.2-3B

Local benchs :

• —PPL 512 eng : 9.37
• —PPL 512 fr : 7.81
• —ARC C LlamaCPP : 47.8
• —ARC E LlamaCPP : 71.4

Training Details

Base Model:

• —Hermes 3B by NousResearch

Fine-Tuning Datasets:

• —Synthetic-Dark-RP
• —Luminous_Opus
• —Synthetic-RP

Tools Used:

• —AutoTrain
• —Axolotl