Quantization made by Richard Erkhov.
MFANN3bv0.4 - bnb 8bits
- Model creator: https://huggingface.co/netcat420/
- Original model: https://huggingface.co/netcat420/MFANN3bv0.4/
Original model description:
library_name: transformers license: apache-2.0 datasets: - netcat420/MFANN pipeline_tag: text-classification
BENCHMARKS: AVG: 62.97 ARC: 60.58 HellaSwag: 76.03 MMLU: 55.8 TruthfulQA: 52.64 Winogrande: 77.83 GSM8K: 55.72
3b variant of MFANNv0.5
fine-tuned on the MFANN dataset which is still a work in progress, and is a chain-of-thought experiment carried out by me and me alone.
