Update README.md

README.md

@@ -41,7 +41,7 @@ Androcles is our inhouse **Prompt Classification Model**, used to classify user
 
 ## Training
 
-Androcles 2 was trained using a mix of https://huggingface.co/datasets/bravesoftware/diverse-llm-prompts-34k & https://huggingface.co/datasets/lmsys/lmsys-chat-1m
+Androcles 2 was trained using a mix of [`bravesoftware/diverse-llm-prompts-34k`](https://huggingface.co/datasets/bravesoftware/androcles-2-chat-50k](https://huggingface.co/datasets/bravesoftware/diverse-llm-prompts-34k)) + labelled data from [`LMSYS/lmsys-chat-1m`](https://huggingface.co/datasets/lmsys/lmsys-chat-1m)
 
 The scripts for training the model & generating the initial dataset can be found [here](https://github.com/brave/Androcles/tree/main)
 
@@ -49,7 +49,7 @@ The scripts for training the model & generating the initial dataset can be found
 
 We use Androcles in a couple of different ways:
 
-* As a first step in our (AI Gateway Server)[https://github.com/brave/ai-gateway/tree/main] powering [Leo](https://brave.com/leo/), classifying prompts into categories with the aim of dynamically changing available tools/instructions depending on what the user asks for - See here [tba]
+* As a first step in our [AI Gateway Server](https://github.com/brave/ai-gateway/tree/main) powering [Leo](https://brave.com/leo/), classifying prompts into categories with the aim of dynamically changing available tools/instructions depending on what the user asks for - See here [tba]
 * As a 'primary category' labeller for our privacy-preserving Leo Analytics server
 
 We host it using Nvidia's Triton Inference Server to serve it with low-latency at scale, but we've also used KServe in the past