Upload README.md with huggingface_hub

README.md

@@ -1,3 +1,43 @@
----
-license: apache-2.0
----
+---
+license: apache-2.0
+base_model: Qwen/Qwen2.5-Coder-7B-Instruct
+tags:
+- kubernetes
+- crd
+- code-generation
+- gguf
+- quantised
+---
+
+# CRD Wizard - Kubernetes CRD Generator (GGUF)
+
+This is a fine-tuned version of **Qwen2.5-Coder-7B-Instruct**, optimized for generating Kubernetes **Custom Resource Definitions (CRDs)** and their corresponding valid YAML manifests.
+
+It was trained to understand CRD Schemas (`openAPIV3Schema`) and produce production-ready YAML examples.
+
+## Model Details
+- **Base Model**: Qwen/Qwen2.5-Coder-7B-Instruct
+- **Format**: GGUF (Q4_K_M Quantization)
+- **Size**: ~4.7 GB
+- **Context Window**: Optimized for **8192** tokens (8k).
+
+## Usage with Ollama
+
+1. Download the `crd-wizard.gguf` and `Modelfile`.
+2. Import into Ollama:
+   ```bash
+   ollama create crd-wizard -f Modelfile
+   ```
+3. Run:
+   ```bash
+   ollama run crd-wizard "Create a PostgresDB resource for the database.my.org/v1 API"
+   ```
+
+## IMPORTANT: Context Window
+This model is optimized for an **8k context window**. 
+If you use the default 32k window of Qwen, it significantly increases memory usage (RAM) and can cause extreme slowness on consumer hardware (e.g., Apple Silicon M1/M2).
+
+The included `Modelfile` enforces this limit:
+```dockerfile
+PARAMETER num_ctx 8192
+```