Upload README.md with huggingface_hub

README.md

@@ -1,13 +1,44 @@
+
 ---
 license: gemma
 language:
 - si
 base_model: google/gemma-2-9b
+library_name: transformers
 ---
+# Gemma2 9B for Sinhala: 100 target vocabulary size + Align target vocabulary initialization + T&B2LS/MTP/512 training
+
+This model is built on top of Gemma2 9B adapted for Sinhala using 30K target language sentences sampled from CC-100.
+
+## Model Details
+
+* **Vocabulary**: This model has an additional 100 target vocabulary.
+* **Target vocabulary initialization**: The target weights of the embedding were initialized using Align initialization.
+* **Training**: This model was additionally pre-trained on 30K target language sentences sampled from CC-100. The training was conducted with the T&B2LS/MTP/512 strategies introduced in the paper.
+
+## Model Description
+
+- **Language:** Sinhala
+- **License:** Gemma Terms of Use
+- **Fine-tuned from model:** google/gemma-2-9b
+
+
+## Model Sources
+
+- **Repository:** https://github.com/gucci-j/lowres-cve
+- **Paper:** https://arxiv.org/abs/2406.11477
+
+## How to Get Started with the Model
+Use the code below to get started with the model.
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
 
-# Sinhala Gemma2-9B model
+model = AutoModelForCausalLM.from_pretrained(
+    "atsuki-yamaguchi/gemma-2-9b-si-30K-align"
+)
+tokenizer = AutoTokenizer.from_pretrained(
+    "atsuki-yamaguchi/gemma-2-9b-si-30K-align"
+)
+```
 
-This model was adapted for Sinhala with 30K target language sentences + Align + T&B 2LS + MTP + 512. 
 
-For technical details, please read the paper: https://arxiv.org/abs/2406.11477.  
-For implementation details, please see the code repository: https://github.com/gucci-j/lowres-cve.