Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
tags:
|
| 6 |
+
- story
|
| 7 |
+
- general usage
|
| 8 |
+
- ultra high precision
|
| 9 |
+
---
|
| 10 |
+
<B>NEO CLASS Ultra Quants for : TinyLlama-1.1B-Chat-v1.0-Ultra-NEO-V1-Imatrix-GGUF</B>
|
| 11 |
+
|
| 12 |
+
The NEO Class tech was created after countless investigations and over 120 lab experiments backed by
|
| 13 |
+
real world testing and qualitative results.
|
| 14 |
+
|
| 15 |
+
<b>NEO Class results: </b>
|
| 16 |
+
|
| 17 |
+
Better overall function, instruction following, output quality and stronger connections to ideas, concepts and the world in general.
|
| 18 |
+
|
| 19 |
+
In addition quants now operate above their "grade" so to speak :
|
| 20 |
+
|
| 21 |
+
IE: Q4 / IQ4 operate at Q5KM/Q6 levels.
|
| 22 |
+
|
| 23 |
+
Likewise for Q3/IQ3 operate at Q4KM/Q5 levels.
|
| 24 |
+
|
| 25 |
+
Perplexity drop of 591 points for Neo Class Imatrix quant of IQ4XS VS regular quant of IQ4XS.
|
| 26 |
+
|
| 27 |
+
(lower is better)
|
| 28 |
+
|
| 29 |
+
For experimental "X" quants of this model please go here:
|
| 30 |
+
|
| 31 |
+
[ https://huggingface.co/DavidAU/TinyLlama-1.1B-Chat-v1.0-Ultra-NEO-V1-X-Imatrix-GGUF ]
|
| 32 |
+
|
| 33 |
+
<B> Model Notes: </B>
|
| 34 |
+
|
| 35 |
+
Maximum context is 2k. Please see original model maker's page for details, and usage information for this model.
|
| 36 |
+
|
| 37 |
+
Special thanks to the model creators at TinyLLama for making such a fantastic model:
|
| 38 |
+
|
| 39 |
+
[ https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0 ]
|