Update README.md

README.md

@@ -22,12 +22,12 @@ pipeline_tag: text-generation
 
 # 🧠 SALAMA LLM — Swahili Instruction-Tuned Text Generation Model
 
-**Developer:** DressMatic AI Labs / EYEDOL Research  
-**Authors:** Israel Adegoke et al.  
+**Developer:** AI4NNOV 
+**Authors:** AI4NNOV.  
 **Version:** v1.0  
 **License:** Apache 2.0  
 **Model Type:** Instruction-Tuned Large Language Model  
-**Base Model:** `unsloth/llama-3.2-3b-instruct`  
+**Base Model:** `Jacaranda/UlizaLlama`  
 
 ---
 
@@ -42,12 +42,12 @@ This model represents a major step in bridging the linguistic digital divide by
 
 ## 🧱 Model Architecture
 
-SALAMA LLM is based on **Unsloth’s optimized Llama-3.2-3B-Instruct**, fine-tuned using **Parameter-Efficient Fine-Tuning (PEFT)** via **LoRA/QLoRA**.  
+SALAMA LLM is based on **Jacaranda/UlizaLlama**, fine-tuned using **Parameter-Efficient Fine-Tuning (PEFT)** via **LoRA/QLoRA**.  
 The architecture supports mixed Swahili-English text inputs while focusing on fluent Swahili text generation for both casual and formal domains.
 
 | Parameter | Value |
 |------------|--------|
-| Base Model | `unsloth/llama-3.2-3b-instruct` |
+| Base Model | `Jacaranda/UlizaLlama` |
 | Fine-Tuning | QLoRA / LoRA (PEFT) |
 | Precision | 4-bit quantization |
 | Optimizer | AdamW |
@@ -128,24 +128,13 @@ print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 
 ---
 
-## 🔍 Model Performance Summary
-
-| Task | Model | F1 | BLEU | ROUGE-L | Accuracy |
-|------|--------|----|-------|----------|-----------|
-| Sentiment Analysis | SALAMA LLM | 0.96 | — | — | 97.9% |
-| Translation | SALAMA LLM | — | 0.49 | 0.61 | — |
-| Q&A | SALAMA LLM | 0.88 | 0.50 | 0.59 | 95.5% |
-| Named Entity Recognition | SALAMA LLM | 0.89 | — | — | — |
-
----
-
 ## ⚡ Key Features
 
-- 🧩 **Optimized for African low-resource NLP contexts**  
-- 💬 **Instruction-following in Swahili and English**  
-- ⚙️ **Lightweight and efficient** (QLoRA-fine-tuned, runs on single 24 GB GPU)  
-- 🌍 **Culturally aligned text generation**  
-- 🪶 **Open-source and extendable** to other African languages  
+- 🧩 Optimized for African low-resource NLP contexts  
+- 💬 Instruction-following in Swahili and English  
+- ⚙️ Lightweight and efficient** (QLoRA-fine-tuned, runs on single 24 GB GPU)  
+- 🌍 Culturally aligned text generation  
+- 🪶 Open-source and extendable to other African languages  
 
 ---
 
@@ -165,36 +154,3 @@ print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 | [`EYEDOL/salama-stt`](https://huggingface.co/EYEDOL/salama-stt) | Swahili Speech-to-Text model (Whisper-small fine-tuned) |
 | [`EYEDOL/salama-tts`](https://huggingface.co/EYEDOL/salama-tts) | Swahili Text-to-Speech model (VITS architecture) |
 
----
-
-## 📜 Citation
-
-If you use this model in your research or development, please cite:
-
-> **Adegoke, I., et al. (2025).** *SALAMA: Scalable African Language Multimodal AI Framework.*  
-> DressMatic AI Labs / EYEDOL Research. Technical Report.
-
----
-
-## 🤝 Acknowledgements
-
-We acknowledge the contributions of:
-
-- **Masakhane** — advancing open African NLP research  
-- **Jacaranda AI** — for UlizaLlama and Swahili pretraining corpora  
-- **Google Research** — for Gemma multilingual models  
-- **Meta AI** — for open-weight Llama foundation models  
-
----
-
-## 🪄 License
-
-This model is released under the **Apache 2.0 License**.  
-You are free to use, modify, and distribute for research and commercial purposes with proper attribution.
-
----
-
-**Model Family:** *SALAMA — Scalable African LAnguage Multimodal AI Framework*  
-**Maintainer:** [EYEDOL Research / DressMatic AI Labs]  
-**Contact:** [email protected]  
-**Repository:** [https://huggingface.co/EYEDOL/salama-llm](https://huggingface.co/EYEDOL/salama-llm)