Document fine-tuned GGUF model

README.md

@@ -1,26 +1,30 @@
 ---
+language:
+- pt
+license: gemma
+library_name: llama.cpp
+pipeline_tag: text-generation
+base_model: empgces/gemma3-270m-grounded-behavior-finetuned-v9
+base_model_relation: quantized
+datasets:
+- empgces/grounded-behavior-n1-pt
 tags:
+- gemma-3
+- fine-tuned
+- finetune
 - gguf
-- llama.cpp
+- q4-k-m
 - unsloth
-
+- grounded-behavior
 ---
 
-# gemma3-270m-grounded-behavior-finetuned-v9-GGUF : GGUF
-
-This model was finetuned and converted to GGUF format using [Unsloth](https://github.com/unslothai/unsloth).
-
-**Example usage**:
-- For text only LLMs:    `llama-cli -hf empgces/gemma3-270m-grounded-behavior-finetuned-v9-GGUF --jinja`
-- For multimodal models: `llama-mtmd-cli -hf empgces/gemma3-270m-grounded-behavior-finetuned-v9-GGUF --jinja`
+# Gemma 3 270M Grounded Behavior — Fine-tuned V9 GGUF
 
-## Available Model files:
-- `gemma-3-270m-it.Q4_K_M.gguf`
+Versão **GGUF `Q4_K_M`** do modelo fine-tuned
+[empgces/gemma3-270m-grounded-behavior-finetuned-v9](https://huggingface.co/empgces/gemma3-270m-grounded-behavior-finetuned-v9).
 
-## Ollama
-An Ollama Modelfile is included for easy deployment.
+O modelo foi treinado sobre `empgces/grounded-behavior-n1-pt` durante
+2 épocas e convertido para GGUF com Unsloth.
 
-## Note
-The model's BOS token behavior was adjusted for GGUF compatibility.
-This was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth)
-[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
+Ao executar com llama.cpp, LM Studio ou Ollama, preserve o chat template Gemma
+incluído no artefacto para manter o mesmo formato usado durante o treino.