Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,25 @@
+---
+license: apache-2.0
+id: heyIamUmair/llama-3.2-3b-merged-gguf
+base_model: unsloth/llama-3.2-3b
+tags:
+- gguf
+- llama.cpp
+- ollama
+- fine-tuned
+- legal
+---
+
+# Llama 3.2 3B Fine-Tuned Legal Model (GGUF)
+
+This is a **fine-tuned Llama 3.2 3B model** on custom legal datasets, merged into a single model and exported in **GGUF** format.
+
+- **Base Model**: unsloth/llama-3.2-3b
+- **Fine-tuning**: Custom legal domain LoRA
+- **Format**: GGUF (FP16)
+- **Usage**: Compatible with `llama.cpp`, `Ollama`, `LM Studio`, `koboldcpp`, etc.
+
+## How to Use with Ollama
+
+```bash
+ollama run llama-3.2-3b-merged-gguf