Update README.md

README.md

@@ -1,21 +1,48 @@
 ---
 base_model: unsloth/gemma-3-1b-it
 tags:
-- text-generation-inference
+- text-generation
+- finetune
 - transformers
 - unsloth
-- gemma3_text
+- gemma3
+- wall-e
 license: apache-2.0
 language:
 - en
+- fa
+- de
 ---
 
-# Uploaded finetuned  model
+# WALL•E — Finetuned Gemma 3 Model
 
-- **Developed by:** sinamsv0
-- **License:** apache-2.0
-- **Finetuned from model :** unsloth/gemma-3-1b-it
+**WALL•E** is a lightweight, multilingual AI model finetuned by **sinamsv0**  
+based on **unsloth/gemma-3-1b-it**.  
+هدف اصلی این مدل ارائه پاسخ‌های دقیق، امن و سازگار برای مکالمه‌های عمومی است.
 
-This gemma3_text model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
+### 🔧 Features
+- **Multilingual ability (EN / فارسی / Deutsch)**
+- **Fast inference** thanks to Unsloth optimizations  
+- **Safety-aligned** for general-purpose assistants  
+- **Lightweight** and suitable for local/edge deployment
 
-[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
+### 🧠 Training
+This model was finetuned using:
+- **Unsloth** (for accelerated training)
+- **HuggingFace TRL**
+- **Custom safety & multi-language dataset**
+
+### 📦 Base Model
+- **unsloth/gemma-3-1b-it**  
+Apache-2.0 licensed.
+
+### 📌 Usage Example
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model = AutoModelForCausalLM.from_pretrained("sinamsv0/WALL-E")
+tokenizer = AutoTokenizer.from_pretrained("sinamsv0/WALL-E")
+
+inputs = tokenizer("Hello WALL•E!", return_tensors="pt")
+outputs = model.generate(**inputs, max_new_tokens=100)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))