README.md updated

.gitignore

@@ -0,0 +1 @@
+._*

README.md

@@ -1,3 +1,34 @@
+# 🐟 Math-A1-2B
+
+**Math-A1-2B** is a 2B-parameter language model by **Kitefish**, focused on mathematical reasoning, symbolic understanding, and structured problem solving.
+
+This is an early release and part of our ongoing effort to build strong, efficient models for reasoning-heavy tasks.
+
 ---
-license: mit
+
+## ✨ What this model is good at
+
+- Basic to intermediate **math problem solving**
+- **Step-by-step reasoning** for equations and word problems
+- Understanding **mathematical symbols and structure**
+- Educational and experimentation use cases
+
 ---
+
+## 🚀 Quick start
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+tokenizer = AutoTokenizer.from_pretrained("kitefish/math-a1-2B")
+model = AutoModelForCausalLM.from_pretrained(
+    "kitefish/math-a1-2B",
+    torch_dtype="auto",
+    device_map="auto"
+)
+
+prompt = "Solve: 2x + 5 = 13"
+inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+
+outputs = model.generate(**inputs, max_new_tokens=100)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))