This repo contains the full precision source code, in "safe tensors" format to generate GGUFs, GPTQ, EXL2, AWQ, HQQ and other formats.
The source code can also be used directly.
You can replace the BASE model with Llama 3.1 model(s) to create a 128k version(s) of this model.
You can also replace the BASE model with Nivida 1,2 or 4 million "Llama 3.1" base models too.
Likewise, you can replace the BASE model with different Llama 3s to create different flavors of this model.
In this merge, the "base" model is consumed (weights replaced) COMPLETELY, yet characteristics of the base model will remain.
If you alter the "weights" (each total 1 (100%) of the 3 models together) to less than 1 -> the remaining will be "BASE" weights and not
all the "weights" of the base model will be consumed / replaced.
You can of course, replace all the models too...
!! => Each of the "weights" apply to 4 layers of the model (32/8) each, you can expand this to 32 to fine tune each layer of each model.
If you want to see what happens when a "base" is replaced ("SuperNova"), and/or the formula is altered (including use of "density" - which causes random pruning) see the models
in the "Dark Planet Wordstorm project" - a collection of 12 modified versions of Dark Planet - each model is unique and different from Dark Planet.
If you are going to use this model, (source, GGUF or a different quant), please review this document for critical parameter, sampler and advance sampler settings (for multiple AI/LLM aps).
This a "Class 1" (settings will enhance operation) model:
For all settings used for this model (including specifics for its "class"), including example generation(s) and for advanced settings guide (which many times addresses any model issue(s)), including methods to improve model performance for all use case(s) as well as chat, roleplay and other use case(s) (especially for use case(s) beyond the model's design) please see:
Regardless of "model class" this document will detail methods to enhance operations.
If the model is a Class 3/4 model the default settings (parameters, samplers, advanced samplers) must be set for "use case(s)" uses correctly. Some AI/LLM apps DO NOT have consistant default setting(s) which result in sub-par model operation. Like wise for Class 3/4 models (which operate somewhat to very differently than standard models) additional samplers and advanced samplers settings are required to "smooth out" operation, AND/OR also allow full operation for use cases the model was not designed for.
BONUS - Use these settings for ANY model, ANY repo, ANY quant (including source/full precision):
This document also details parameters, sampler and advanced samplers that can be use FOR ANY MODEL, FROM ANY REPO too - all quants, and of course source code operation too - to enhance the operation of any model.
I strongly suggest you also visit the DavidAU GGUF (below) repo too for more details in using this model ; especially if it is "Class 3" or "Class 4" to get maximum performance from the model.
