Update README.md

README.md

@@ -29,11 +29,11 @@ We will release more details in the upcoming technical report.
 - **Model type:** A 7B parameter model fine-tuned on a mix of publicly available, synthetic datasets on translation-related tasks, as well as conversational datasets and code instructions.
 - **Language(s) (NLP):** English, Portuguese, Spanish, French, German, Dutch, Italian, Korean, Chinese, Russian
 - **License:** CC-BY-NC-4.0
-- **Finetuned from model:** TowerBase [ADD LINK]
+- **Finetuned from model:** [TowerBase](https://huggingface.co/datasets/Unbabel/TowerBlocks-v0.1)
 
 ## Intended uses & limitations
 
-The model was initially fine-tuned on a filtered and preprocessed supervised fine-tuning dataset (TowerBlocks [ADD LINK]), which contains a diverse range of data sources:
+The model was initially fine-tuned on a filtered and preprocessed supervised fine-tuning dataset ([TowerBlocks](https://huggingface.co/datasets/Unbabel/TowerBlocks-v0.1)), which contains a diverse range of data sources:
 - Translation
 - Automatic Post Edition
 - Machine Translation Evaluation
@@ -45,7 +45,7 @@ The model was initially fine-tuned on a filtered and preprocessed supervised fin
 - Synthetic Chat data 
 - Code instructions
 
-You can find the dataset and all data sources of TowerBlocks [ADD LINK] here.
+You can find the dataset and all data sources of [TowerBlocks](https://huggingface.co/datasets/Unbabel/TowerBlocks-v0.1) here.
 
 Here's how you can run the model using the `pipeline()` function from 🤗 Transformers:
 
@@ -95,13 +95,13 @@ TowerInstruct-v0.1 was trained using the ChatML prompt templates without any sys
 
 ### Supervised tasks
 
-The prompts for all supervised tasks can be found in TowerBlocks [ADD LINK]. We have used multiple prompt templates for each task. While different prompts may offer different outputs, the difference in downstream performance should be very minimal.
+The prompts for all supervised tasks can be found in [TowerBlocks](https://huggingface.co/datasets/Unbabel/TowerBlocks-v0.1). We have used multiple prompt templates for each task. While different prompts may offer different outputs, the difference in downstream performance should be very minimal.
 
 ## Training Details
 
 ### Training Data
 
-Link to TowerBlocks [ADD LINK].
+Link to [TowerBlocks](https://huggingface.co/datasets/Unbabel/TowerBlocks-v0.1).
 
 #### Training Hyperparameters