license: apache-2.0
language:
- en
tags:
- story
- general usage
- roleplay
- creative
- rp
- fantasy
- story telling
- ultra high precision
NEO CLASS Ultra Quants for : L3-8B-Stheno-v3.2
Additional quants are uploading...
The NEO Class tech was created after countless investigations and over 120 lab experiments backed by real world testing and qualitative results.
NEO Class results:
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 1191 points for Neo Class Imatrix quant of IQ4XS VS regular quant of IQ4XS.
(lower is better)
A Funny thing happened on the way to the "lab" ...
Although this model uses a "Llama3" template we found that Command-R's template worked better specifically for creative purposes.
This applies to both normal quants and Neo quants.
Here is Command-R's template:
{ "name": "Cohere Command R", "inference_params": { "input_prefix": "<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|USER_TOKEN|>", "input_suffix": "<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>", "antiprompt": [ "<|START_OF_TURN_TOKEN|>", "<|END_OF_TURN_TOKEN|>" ], "pre_prompt_prefix": "<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>", "pre_prompt_suffix": "" } }
This was "interesting" issue was confirmed by multiple users.
Model Notes:
Maximum context is 8k. Please see original model maker's page for details, and usage information for this model.
Special thanks to the model creators at SAO10K for making such a fantastic model: