Update README.md

README.md

@@ -24,9 +24,11 @@ tags:
 
 # 🌳 BaobabAI v0.2
 
-**Africa's first continental AI model** — built to serve 1.4 billion Africans in their own languages.
+**Africa's first continental AI model** — now with 15 languages 
+and 86,604 training pairs.
 
-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.
+Named after the Baobab tree — the Tree of Life across Africa.
+Lives 2,000+ years. Feeds entire ecosystems. That is the vision.
 
 ---
 
@@ -34,7 +36,7 @@ Named after the Baobab tree — the Tree of Life across Africa. Lives 2,000+ yea
 - 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
+- Training loss improved: 2.81 → 2.07
 - New data sources: Glot500 + CulturaX + Masakhane
 
 ---
@@ -50,10 +52,10 @@ Named after the Baobab tree — the Tree of Life across Africa. Lives 2,000+ yea
 | Amharic | Ethiopia | 35M+ |
 | Somali | Somalia/Kenya | 20M+ |
 | Xhosa | South Africa | 27M+ |
+| Zulu | 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+ |
 
@@ -63,12 +65,12 @@ Named after the Baobab tree — the Tree of Life across Africa. Lives 2,000+ yea
 | Parameter | Value |
 |-----------|-------|
 | Base Model | Llama 3.2 3B Instruct |
-| Training pairs | 86,604 |
-| Training steps | 500 |
-| Final loss | 2.07 |
+| 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 |
+| Data Sources | Masakhane, Glot500, CulturaX |
 
 ---
 
@@ -85,8 +87,8 @@ Named after the Baobab tree — the Tree of Life across Africa. Lives 2,000+ yea
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
-model = AutoModelForCausalLM.from_pretrained("okaforpascal40/BaobabAI-v0.2")
 tokenizer = AutoTokenizer.from_pretrained("okaforpascal40/BaobabAI-v0.2")
+model = AutoModelForCausalLM.from_pretrained("okaforpascal40/BaobabAI-v0.2")
 ```
 
 ---
@@ -100,9 +102,9 @@ tokenizer = AutoTokenizer.from_pretrained("okaforpascal40/BaobabAI-v0.2")
 ---
 
 ## 👨🏿‍💻 Built By
-**Pascal Okafor Ogbonna**
-Founder & CTO, SabiFlow Technologies Limited
-🌍 Nigeria | github.com/okaforpascal400/BaobabAI
+Pascal Okafor Ogbonna | SabiFlow Technologies Limited
+🌍 [baobabai.dev](https://baobabai.dev) · 
+[GitHub](https://github.com/okaforpascal400/BaobabAI)
 
 ---