DevQuasar
/

HermesNova-Llama-3.1-8B-GGUF

Inference Endpoints

Model card Files Files and versions Community

Quantized version of DevQuasar/HermesNova-Llama-3.1-8B

I'm doing this to 'Make knowledge free for everyone', using personal time and resources.

If you want to support my efforts please visit my ko-fi page: https://ko-fi.com/devquasar

Also feel free to visit my website https://devquasar.com/

Downloads last month: 21

GGUF

Model size

8.03B params

Architecture

llama

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference API

Unable to determine this model's library. Check the docs .

Model tree for DevQuasar/HermesNova-Llama-3.1-8B-GGUF

Base model

DevQuasar/HermesNova-Llama-3.1-8B

Quantized

(4)

this model

Collection including DevQuasar/HermesNova-Llama-3.1-8B-GGUF

GGUFs

quantized models • 174 items • Updated 1 day ago • 1

Evaluation results

acc_norm on bbh
self-reported

0.542
acc_norm on gpqa
self-reported

0.337
exact_match on math
self-reported

0.115
acc_norm on mmlu
self-reported

0.373
acc_norm on musr
self-reported

0.433
acc on hellaswag
self-reported

0.631
acc_norm on hellaswag
self-reported

0.818

View on Papers With Code