Text Generation
Transformers
Safetensors
llama
mergekit
Merge
llama-3
creative
creative writing
fiction writing
plot generation
sub-plot generation
story generation
scene continue
storytelling
fiction story
science fiction
romance
all genres
story
writing
vivid prose
vivid writing
fiction
roleplaying
bfloat16
swearing
rp
llama3
llama-3.1
llama 3.1
llama3.1
horror
finetune
conversational
text-generation-inference
Update README.md
Browse files
README.md
CHANGED
|
@@ -133,10 +133,16 @@ dtype: bfloat16
|
|
| 133 |
|
| 134 |
NOTE:
|
| 135 |
|
| 136 |
-
You can replace the BASE model with Llama 3.1 to create a 128k version(s) of this model.
|
|
|
|
|
|
|
| 137 |
|
| 138 |
Likewise, you can replace the BASE model with different Llama 3s to create different flavors of this model.
|
| 139 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 140 |
You can of course, replace all the models too...
|
| 141 |
|
| 142 |
!! => Each of the "weights" apply to 4 layers of the model (32/8), you can expand this to 32 to fine tune each layer of each model.
|
|
|
|
| 133 |
|
| 134 |
NOTE:
|
| 135 |
|
| 136 |
+
You can replace the BASE model with Llama 3.1 model(s) to create a 128k version(s) of this model.
|
| 137 |
+
|
| 138 |
+
You can also replace the BASE model with Nivida 1,2 or 4 million "Llama 3.1" base models too.
|
| 139 |
|
| 140 |
Likewise, you can replace the BASE model with different Llama 3s to create different flavors of this model.
|
| 141 |
|
| 142 |
+
In this merge, the "base" model is consumed (weights replaced) COMPLETELY, yet characteristics of the base model will remain.
|
| 143 |
+
|
| 144 |
+
If you alter the "weights" (each total 1 of the 3 models) to less than 1 -> the remaining will be "BASE" weights.
|
| 145 |
+
|
| 146 |
You can of course, replace all the models too...
|
| 147 |
|
| 148 |
!! => Each of the "weights" apply to 4 layers of the model (32/8), you can expand this to 32 to fine tune each layer of each model.
|