|
--- |
|
license: apache-2.0 |
|
language: |
|
- en |
|
tags: |
|
- story |
|
- general usage |
|
- ultra high precision |
|
pipeline_tag: text-generation |
|
--- |
|
<B>NEO CLASS Ultra Quants for : TinyLlama-1.1B-Chat-v1.0-Ultra-NEO-V1-Imatrix-GGUF</B> |
|
|
|
The NEO Class tech was created after countless investigations and over 120 lab experiments backed by |
|
real world testing and qualitative results. |
|
|
|
<b>NEO Class results: </b> |
|
|
|
Better overall function, instruction following, output quality and stronger connections to ideas, concepts and the world in general. |
|
|
|
In addition quants now operate above their "grade" so to speak : |
|
|
|
IE: Q4 / IQ4 operate at Q5KM/Q6 levels. |
|
|
|
Likewise for Q3/IQ3 operate at Q4KM/Q5 levels. |
|
|
|
Perplexity drop of 591 points for Neo Class Imatrix quant of IQ4XS VS regular quant of IQ4XS. |
|
|
|
(lower is better) |
|
|
|
For experimental "X" quants of this model please go here: |
|
|
|
[ https://huggingface.co/DavidAU/TinyLlama-1.1B-Chat-v1.0-Ultra-NEO-V1-X-Imatrix-GGUF ] |
|
|
|
<B> Model Notes: </B> |
|
|
|
Maximum context is 2k. Please see original model maker's page for details, and usage information for this model. |
|
|
|
Special thanks to the model creators at TinyLLama for making such a fantastic model: |
|
|
|
[ https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0 ] |
