Create README.md

README.md

@@ -0,0 +1,44 @@
+---
+tags:
+- mlx
+- apple-silicon
+- text-generation
+- gemma3
+- instruction-tuned
+library_name: mlx-lm
+pipeline_tag: text-generation
+base_model: Daizee/Dirty-Calla-4B
+license: apache-2.0
+---
+
+# 🖤 Dirty-Calla-4B — **MLX** builds for Apple Silicon
+
+**Dirty-Calla-4B-mlx** provides Apple Silicon–optimized versions of **Daizee/Dirty-Calla-4B**, a fine-tuned **Gemma 3 (4B)** model developed by **Daizee** for expressive, humanlike, and emotionally textured responses.
+
+This conversion uses Apple’s **MLX** framework for local inference on **M1, M2, and M3 Macs**.  
+Each variant trades size for speed or precision, so you can choose what fits your workflow.
+
+> 🧩 **Note on vocab padding:**  
+> The tokenizer and embedding matrix were padded to the next multiple of 64 tokens (262,208 total).  
+> Added tokens are labeled `<pad_ex_*>` — they will not appear in normal generations.
+
+---
+
+## ⚙️ Variants
+
+| Folder        | Bits | Group Size | Description |
+|----------------|------|------------|--------------|
+| `mlx/g128/`   | int4 | 128 | Smallest & fastest (lightest memory use) |
+| `mlx/g64/`    | int4 | 64  | Balanced: slightly slower, more stable |
+| `mlx/int8/`   | int8 | —   | Closest to fp16 precision, best coherence |
+
+---
+
+## 🚀 Quickstart
+
+### Run directly from Hugging Face
+```bash
+python -m mlx_lm.generate \
+  --model hf://Daizee/Dirty-Calla-4B-mlx/mlx/g64 \
+  --prompt "Describe a rainy city from the perspective of a poet." \
+  --max-tokens 150 --temp 0.4