Hugging Face's logo

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

Text Generation
Transformers
Safetensors
English
llama
Llama-3
instruct
finetune
chatml
gpt4
synthetic data
distillation
function calling
json mode
axolotl
roleplaying
chat
conversational
Eval Results
text-generation-inference
Inference Endpoints
Model card Files Community
1

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
Downloads last month
136
Safetensors
Model size
3.21B params
Tensor type
BF16
·
Inference Providers NEW
Text Generation
This model is not currently available via any of the supported Inference Providers.

Model tree for Nexesenex/mrcuddle_Dark-Hermes3-Llama3.2-3B

Base model

NousResearch/Hermes-3-Llama-3.2-3B
Finetuned
(9)
this model
Merges
3 models

Evaluation results

View on Papers With Code