Update README.md

README.md

@@ -8,7 +8,6 @@ tags:
 - llama-factory
 - lora
 - llama-cpp
-- gguf-my-repo
 datasets:
 - allura-org/fujin-cleaned-stage-1
 - Dampfinchen/Creative_Writing_Multiturn
@@ -21,11 +20,11 @@ datasets:
 
 # IntelligentEstate/Jaberwocky-VEGA-qwn25-Q_8_0-GGUF
 
-Jaberwocky is a Small edge assistant model
+Jaberwocky is a Small edge assistant model primarily for edge uses as a guy in the chair for custom dialog
 
 ![jabberwocki.png](https://cdn-uploads.huggingface.co/production/uploads/6593502ca2607099284523db/CblqVOZLgAAURnPH8qZYU.png)
 
-This model was converted to GGUF format from [`Alfitaria/Q25-1.5B-VeoLu`](https://huggingface.co/Alfitaria/Q25-1.5B-VeoLu) using llama.cpp
+This model was converted to GGUF format from [`Alfitaria/Q25-1.5B-VeoLu`](https://huggingface.co/Alfitaria/Q25-1.5B-VeoLu) using an imortance matrix to smooth the gradient via llama.cpp
 Refer to the [original model card](https://huggingface.co/Alfitaria/Q25-1.5B-VeoLu) for more details on the model.
 
 ## Use with llama.cpp
@@ -35,4 +34,4 @@ Install llama.cpp through brew (works on Mac and Linux)
 brew install llama.cpp
 
 ```
-Invoke the llama.cpp server or the CLI.
+Invoke the llama.cpp server or the CLI.