Update README.md

README.md

@@ -42,9 +42,9 @@ print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 ```
 
 ### Training Procedure
-- **Dataset:** Semi-automated English-to-Arabic translation with human refinement.
-- **Training Resources:** 632 million healthcare specialized tokens.
-- **Evaluation:**
+- **Dataset:** BiMed1.3M, 632 million healthcare specialized tokens.
+- **QLoRA Adaptation:** Implements a low-rank adaptation technique, incorporating learnable low-rank adapter weights into the experts and the routing network. This results in training about 4% of the original parameters.
+- **Training Resources:** The model underwent training on approximately 632 million tokens from the Arabic-English corpus, including 288 million tokens exclusively for English.
 
 ### Model Performance
 - **Benchmarks:** Outperforms the baseline model and Jais-30B in medical evaluations.
@@ -62,10 +62,9 @@ print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 ### Safety and Ethical Considerations
 - **Usage:** Research purposes only.
 
-
 ### Accessibility
 - **Availability:** [BiMediX GitHub Repository](https://github.com/mbzuai-oryx/BiMediX).
 
 ### Authors
-Sara Pieri, Sahal Shaji Mullappilly, Fahad Shahbaz Khan, Rao Muhammad Anwer Salman Khan, Timothy Baldwin, Hisham Cholakkal, Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI).
-
+Sara Pieri, Sahal Shaji Mullappilly, Fahad Shahbaz Khan, Rao Muhammad Anwer Salman Khan, Timothy Baldwin, Hisham Cholakkal  
+**Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI)**