Update README.md

README.md

@@ -162,7 +162,7 @@ For a better experience, we recommend using [the following generation parameters
 
 ### Training Data
 
-A combination of both public and private datasets designed in the IIC. The dataset consists of 21975 conversations in Spanish, with the format `chatml` and has the same structure as the [Anthropic/hh-rlhf dataset](https://huggingface.co/datasets/Anthropic/hh-rlhf). Each conversation has two variants: `chosen` and `rejected`, and only differs the last answer of the assistant. The last answer in the `chosen` variant is considered a better answer than the one in the `rejected` variant. Different techniques have been used to generate the dataset, which we explain in depth in the paper (**coming soon**).
+A combination of both public and private datasets designed in the IIC. The dataset consists of 21975 conversations in Spanish, with the format `chatml` and has the same structure as the [Anthropic/hh-rlhf dataset](https://huggingface.co/datasets/Anthropic/hh-rlhf). Each conversation has two variants: `chosen` and `rejected`, and only differs the last answer of the assistant. The last answer in the `chosen` variant is considered a better answer than the one in the `rejected` variant. Different techniques have been used to generate the dataset, which we explain in depth in the research (**coming soon**).
 
 ### Training Procedure
 
@@ -224,7 +224,11 @@ As can be seen in the time used, in eight and a half hours we have managed to im
 
 ## Evaluation
 
-<!-- This section describes the evaluation protocols and provides the results. -->
+To evaluate, we use the following datasets:
+
+1. [IIC/AQuAS](https://huggingface.co/datasets/IIC/AQuAS).
+2. [IIC/RagQuAS](https://huggingface.co/datasets/IIC/RagQuAS).
+3. privados
 
 ### Testing Data, Factors & Metrics