---
base_model: Nitral-AI/Sekhmet_Aleph-L3.1-8B-v0.1
language:
- en
license: other
pipeline_tag: text-generation
quantized_by: Reiterate3680
---
# Not reccomended for use with context sizes above 8192 ([#8676](https://github.com/ggerganov/llama.cpp/pull/8676))

Original Model: https://huggingface.co/Nitral-AI/Sekhmet_Aleph-L3.1-8B-v0.1

made with https://huggingface.co/FantasiaFoundry/GGUF-Quantization-Script 

using Q_8 output tensors and token embeddings

using bartowski's imatrix dataset