Add README

README.md

@@ -3,7 +3,7 @@ tags:
 - gguf
 - llama.cpp
 - unsloth
-
+- vision-language-model
 ---
 
 # LLAMA-JSON-data-extration - GGUF
@@ -15,7 +15,18 @@ This model was finetuned and converted to GGUF format using [Unsloth](https://gi
 - For multimodal models: **llama-mtmd-cli** **-m** model_name.gguf **--mmproj** mmproj_file.gguf
 
 ## Available Model files:
-- `llama-3.2-3b-instruct.Q8_0.gguf`
+- `gemma-3-4b-it.Q8_0.gguf`
+- `gemma-3-4b-it.BF16-mmproj.gguf`
+
+## ⚠️ Ollama Note for Vision Models
+**Important:** Ollama currently does not support separate mmproj files for vision models.
+
+To create an Ollama model from this vision model:
+1. Place the `Modelfile` in the same directory as the finetuned bf16 merged model
+3. Run: `ollama create model_name -f ./Modelfile`
+   (Replace `model_name` with your desired name)
+
+This will create a unified bf16 model that Ollama can use.
 
-## Ollama
-An Ollama Modelfile is included for easy deployment.
+## Note
+The model's BOS token behavior was adjusted for GGUF compatibility.