Update README.md

README.md

@@ -57,7 +57,7 @@ used.
 The application configuration points to the following default local model path:
 
 ```text
-is-leeroy-jenkins/gemma-3-270m-it-Q4_K_M.gguf
+buddy/gemma-3-270m-it-Q4_K_M.gguf
 ```
 
 The runtime loads the model through `Llama(...)` from `llama_cpp`, and the application defaults to a
@@ -120,7 +120,7 @@ Typical usage scenarios include:
 from llama_cpp import Llama
 
 llm = Llama(
-    model_path="is-leeroy-jenkins/gemma-3-270m-it-Q4_K_M.gguf",
+    model_path="buddy/gemma-3-270m-it-Q4_K_M.gguf",
     n_ctx=4096,
 )
 
@@ -138,7 +138,7 @@ print(response["choices"][0]["message"]["content"])
 
 ```bash
 ./llama-cli \
-  -m is-leeroy-jenkins/gemma-3-270m-it-Q4_K_M.gguf\
+  -m buddy\gemma-3-270m-it-Q4_K_M.gguf\
   -c 4096 \
   -p "Write a short description of buddy."
 ```
@@ -169,7 +169,7 @@ consumer hardware, but it may also reduce generation quality relative to higher-
 The following points are supported by the buddy source files:
 
 * the application expects a model file named `llm/gemma-3-270m-it-Q4_K_M.gguf`
-* the configured model path is `is-leeroy-jenkins/gemma-3-270m-it-Q4_K_M.gguf`
+* the configured model path is `buddy/gemma-3-270m-it-Q4_K_M.gguf`
 * inference is performed through `llama-cpp-python`
 * the application uses a 4096-token context window by default
 * the application combines local text generation with embedding-based retrieval components
@@ -264,7 +264,7 @@ This repository is expected to contain:
 
 ```text
 README.md
-is-leeroy-jenkins/gemma-3-270m-it-Q4_K_M.gguf
+buddy/gemma-3-270m-it-Q4_K_M.gguf
 ```
 
 ## Relationship to the Main buddy Repository