RichardErkhov's picture
uploaded readme
89caca9 verified
|
raw
history blame
916 Bytes

Quantization made by Richard Erkhov.

Github

Discord

Request more models

MFANN3bv0.7 - bnb 8bits

Original model description:

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

MFANN 3b version 0.7

image/png

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

62.98 <- Average 61.69 <- ARC 75.98 <- HellaSwag 55.4 <- MMLU 53.49 <- TruthfulQA 77.66 <- Winogrande (this models strong-suit) 53.68 <- GSM8K

this model is completely uncensored