RichardErkhov/netcat420_-_MFANN3bv0.6-8bits

Quantization made by Richard Erkhov.

Github

Discord

Request more models

MFANN3bv0.6 - bnb 8bits

• Model creator: https://huggingface.co/netcat420/
• Original model: https://huggingface.co/netcat420/MFANN3bv0.6/

Original model description:

library_name: transformers license: apache-2.0 datasets: - netcat420/MFANN pipeline_tag: text-classification

MFANN 3b version 0.6

fine-tuned on the MFANN dataset as it stands on 5/2/2024 as it is an ever changing and expaning dataset.

benchmark results for this 3b model:

64.34 <-- Average 62.63 <-- Arc 77.1 <-- HellaSwag 58.43 <-- MMLU 51.71 <-- TruthfulQA 74.66 <-- Winogrande 61.49 <-- GSM8K

currently the worlds best 2.78B parameter model!!!!!!!!!!! as of 5/2/2024