Update README.md

README.md

@@ -1,21 +1,114 @@
 ---
-base_model: unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit
+language:
+- ha
+- ig
+- pcm
+- yo
+- sw
+- am
+- so
+- xh
+- sn
+- lg
+- ln
+- zu
+- wo
+- om
+license: apache-2.0
 tags:
-- text-generation-inference
-- transformers
-- unsloth
+- africa
 - llama
-license: apache-2.0
-language:
-- en
+- fine-tuned
+- multilingual
+---
+
+# 🌳 BaobabAI v0.2
+
+**Africa's first continental AI model** — built to serve 1.4 billion Africans in their own languages.
+
+Named after the Baobab tree — the Tree of Life across Africa. Lives 2,000+ years. Feeds entire ecosystems. That is the vision for this model.
+
+---
+
+## 🚀 What's New in v0.2
+- 3x more training data — 86,604 training pairs
+- 5x more training steps — 500 steps
+- 4 new languages added
+- Training loss improved from 2.81 → 2.07
+- New data sources: Glot500 + CulturaX + Masakhane
+
 ---
 
-# Uploaded finetuned  model
+## 🌍 Languages Supported
+| Language | Country | Speakers |
+|----------|---------|----------|
+| Hausa | Nigeria/Niger/Chad | 70M+ |
+| Yoruba | Nigeria/Benin/Togo | 45M+ |
+| Igbo | Nigeria | 30M+ |
+| Nigerian Pidgin | West Africa | 75M+ |
+| Swahili | Kenya/Tanzania | 200M+ |
+| Amharic | Ethiopia | 35M+ |
+| Somali | Somalia/Kenya | 20M+ |
+| Xhosa | South Africa | 27M+ |
+| Shona | Zimbabwe | 15M+ |
+| Luganda | Uganda | 8M+ |
+| Lingala | DRC/Congo | 70M+ |
+| Zulu | South Africa | 27M+ |
+| Wolof | Senegal/Gambia | 12M+ |
+| Oromo | Ethiopia/Kenya | 40M+ |
 
-- **Developed by:** okaforpascal40
-- **License:** apache-2.0
-- **Finetuned from model :** unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit
+---
+
+## 📊 Training Details
+| Parameter | Value |
+|-----------|-------|
+| Base Model | Llama 3.2 3B Instruct |
+| Training pairs | 86,604 |
+| Training steps | 500 |
+| Final loss | 2.07 |
+| Method | QLoRA (r=16) via Unsloth |
+| Hardware | NVIDIA Tesla T4 |
+| Data sources | Masakhane, Glot500, CulturaX |
+
+---
 
-This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
+## 💡 What BaobabAI Can Do
+- Summarize African news articles in local languages
+- Identify African languages automatically
+- Answer questions about African topics
+- Process Nigerian Pidgin English natively
+- Classify African content by category
+
+---
+
+## 🔧 Quick Start
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model = AutoModelForCausalLM.from_pretrained("okaforpascal40/BaobabAI-v0.2")
+tokenizer = AutoTokenizer.from_pretrained("okaforpascal40/BaobabAI-v0.2")
+```
+
+---
+
+## 🗺️ Roadmap
+- v0.3 — 20 languages, 200,000+ training pairs
+- v0.5 — Upgrade to 8B model
+- v1.0 — Live REST API, enterprise ready
+- v2.0 — Continental dominance, 50+ languages
+
+---
+
+## 👨🏿‍💻 Built By
+**Pascal Okafor Ogbonna**
+Founder & CTO, SabiFlow Technologies Limited
+🌍 Nigeria | github.com/okaforpascal400/BaobabAI
+
+---
+
+## 📜 License
+Apache 2.0 — free to use, modify and build on.
+
+---
 
-[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
+*The tree is planted. The continent will feel its shade.* 🌳