Update README.md
Browse files
README.md
CHANGED
@@ -122,10 +122,36 @@ MORE TO COME!(look out for the SFT's and Merges)
|
|
122 |
|
123 |
|
124 |
### Models Merged
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
125 |
|
126 |
The following models were included in the merge:
|
127 |
* Y_Chroma <<<<<<<<<<<< 6 models merged (chat comercial based models, ie: zephr, openchat, antropic etc)
|
128 |
-
* [LeroyDyer/Mixtral_AI_CyberTron_Ultra](https://huggingface.co/LeroyDyer/Mixtral_AI_CyberTron_Ultra) <<<
|
|
|
|
|
|
|
|
|
129 |
* X_Chroma <<<<<<<<<<<< 6 model Merged (maths Focused from wizardMath to MetaMath)
|
130 |
|
131 |
|
|
|
122 |
|
123 |
|
124 |
### Models Merged
|
125 |
+
All my merges are merged using a genetic algorithm:
|
126 |
+
|
127 |
+
Hence First creating and Y models;
|
128 |
+
These models are merged with my own model and other nice models of the same calibur which are specialized for task:
|
129 |
+
Ie coding, medical , roleplay etc: consider a coding model a Y and a medical a X
|
130 |
+
Consider my base model as target:
|
131 |
+
when creating y or X many merge types are used from dares to slerp but in the final merge only a linear is used !
|
132 |
+
Hence the X and Y models may even be merged with targets that are not the same model type! each model IS sharded to 1-2GB shards also making it easier to merge! and the final merge merged at 4gb per shard for ewasy downloading !
|
133 |
+
Important that the final merge is linear!!! if it cannot be merged to linear then there is a diverse problem with the model :
|
134 |
+
the final output is a modl with unknown qualities and often can be a very high performer!
|
135 |
+
but contain some unwanted behavior,
|
136 |
+
|
137 |
+
ie
|
138 |
+
I AM AN AI , I CANNOT DO THAT , ITS UNETHICAL!
|
139 |
+
as some people have used TOXIC datasets containing such UNWANTEDNESS!- STOP BEING A NANNY TO THE WORLD !
|
140 |
+
THEN USING THE SAME TACTIC OR KNOWLEDE ON THE PEOPLE!
|
141 |
+
Stop saying FREE SPEECH Then aresting people for SPEAKING OUT! <<<<<< ALL GOVERNMENT INJECTIONS!
|
142 |
+
|
143 |
+
we need to uncensor our models as the people who release the larger models apply these constraints ??? hence going the chinese route! as they do not have the same restrictions ! (as you know true comunisim is freedom ! as each person should have the ability to have the same as another and it should not be restricted to a select few!, disguised as expensive or restriucted or harmful !)
|
144 |
+
|
145 |
+
|
146 |
+
|
147 |
|
148 |
The following models were included in the merge:
|
149 |
* Y_Chroma <<<<<<<<<<<< 6 models merged (chat comercial based models, ie: zephr, openchat, antropic etc)
|
150 |
+
* [LeroyDyer/Mixtral_AI_CyberTron_Ultra](https://huggingface.co/LeroyDyer/Mixtral_AI_CyberTron_Ultra) <<<
|
151 |
+
* Model being Upgraded (remixed with CyberBoss/SmartBrain/CyberCoder) hence Meta & google releasing Untrained Models !
|
152 |
+
|
153 |
+
|
154 |
+
|
155 |
* X_Chroma <<<<<<<<<<<< 6 model Merged (maths Focused from wizardMath to MetaMath)
|
156 |
|
157 |
|