Update README.md (#3)

- Update README.md (1dec455ecc08d88167a06865afdb964a876f6345)


Co-authored-by: Amril Nurman <[email protected]>

README.md

@@ -10,9 +10,37 @@ language:
 pipeline_tag: text-generation
 ---
 
-# Qwen3-1.7B (from-scratch, 41B-token pretrain)
+# QVAC Genesis I Pretrained Model
 
-A 1.7B-parameter decoder-only transformer (Qwen3 family) pre-trained **from scratch** on ~**40B tokens** of multi-domain text with **BF16 mixed precision** and a **4,096-token** context. Checkpoints are provided in standard Hugging Face format for easy inference and fine-tuning.
+## Key Highlights
+- **Pretrained on the Largest Synthetic Educational Dataset**  
+  This model has been **pretrained on Tether's QVAC Genesis I**, the largest synthetic dataset released for educational LLM pre-training.
+
+  The model was trained **from scratch** on approximately **41B tokens** of multi-domain educational text, using **BF16 mixed precision** and a **4,096-token context window**. Training was made with a **Qwen3-family 1.7B-parameter decoder-only transformer** architecture.
+
+  Checkpoints are provided in standard Hugging Face format for easy inference, continual pre-training, and fine-tuning.
+
+- **Multi-Domain Educational Coverage**  
+  Because the model is trained on QVAC Genesis I, it inherits curriculum-aligned coverage across:  
+  - Mathematics  
+  - Physics  
+  - Biology  
+  - Medicine  
+
+- **Superior Benchmark Performance**  
+  Leveraging QVAC Genesis I as its training foundation, the model consistently outperforms baselines in:  
+  - Reasoning tasks  
+  - Knowledge assessments  
+  - Subject-specific QA  
+
+- **First Publicly Released Education-Specific Pretrained Model**  
+  This is the first open-source pretrained model built directly on a rigorously validated synthetic dataset for education, offering deep and comprehensive STEM coverage.
+abilities  
+
+## Intended Uses
+- Continual pre-training or fine-tuning for educational applications (STEM-focused tutoring, QA systems, curriculum support)  
+- Benchmarking reasoning and subject-specific QA performance  
+- Research into synthetic dataset–driven LLM training  
 
 ---