Update README.md

README.md

@@ -201,7 +201,7 @@ model-index:
 # Model Summary
 
 The SantaCoder models are a series of 1.1B parameter models trained on the Python, Java, and JavaScript subset of [The Stack (v1.1)](https://huggingface.co/datasets/bigcode/the-stack) (which excluded opt-out requests). 
-The main model uses multi-query attention, was trained using near-deduplication and comment-to-code ratio as filtering criteria and using the Fill-in-the-Middle objective.
+The main model uses [Multi Query Attention](https://arxiv.org/abs/1911.02150), was trained using near-deduplication and comment-to-code ratio as filtering criteria and using the [Fill-in-the-Middle objective](https://arxiv.org/abs/2207.14255).
 In addition there are several models that were trained on datasets with different filter parameters and with architecture and objective variations. 
 
 - **Repository:** [bigcode/Megatron-LM](https://github.com/bigcode-project/Megatron-LM)
@@ -221,7 +221,7 @@ In addition there are several models that were trained on datasets with differen
 |`dedup-alt`| MQA | AR + FIM | Stronger near-deduplication |
 |`final`| MQA | AR + FIM | Stronger near-deduplication and comment-to-code ratio |
 
-The `final` model is the best performing model and was trained twice as long as the others. This checkpoint is the default model and available on the `main` branch. All other checkpoints are on separate branches with according names.
+The `final` model is the best performing model and was trained twice as long (236B tokens) as the others. This checkpoint is the default model and available on the `main` branch. All other checkpoints are on separate branches with according names.
 
 # Use