Update README.md

README.md

@@ -97,7 +97,7 @@ library_name: transformers
 <details>
 <summary>Click to expand</summary>
 
-- [Llama-3.1-Carballo](#llama31-carballo)
+- [Llama-3.1-Carballo](#llama-31-carballo)
   - [Table of Contents](#table-of-contents)
   - [Model description](#model-description)
   - [Intended uses and limitations](#intended-uses-and-limitations)
@@ -120,7 +120,7 @@ library_name: transformers
 **Llama-3.1-Carballo** is a 8B-parameter transformer-based causal language model for Galician, Portuguese, Spanish, Catalan and English. 
 It is the result of a continual pretraining of [meta-llama/Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) with a multilingual corpus of almost 20B tokens, with an emphasis on Galician texts.
 
-This model is part of the **Carballo familily**, a family of LLMs specialized in Galician. Smaller models can be founded [here](https://huggingface.co/collections/proxectonos/text-models-65d49fa54e358ce02a9699c8)
+This model is part of the **Carballo familily**, a family of LLMs specialized in Galician. Smaller models can be found [here](https://huggingface.co/collections/proxectonos/text-models-65d49fa54e358ce02a9699c8)
 ## Intended uses and limitations
 
 The **Llama-3.1-Carballo** model is ready-to-use only for causal language modeling. 
@@ -193,7 +193,7 @@ The corpus is structured as follows:
 - num_epochs: 1.0
 
 ### Framework
-The traininf was conducted in the Galicia Supercomputing Center ([CESGA](https://www.cesga.es/en/home-2/)), using 5 nodes with 2 GPUs NVIDIA A100 each one.
+The training was conducted in the Galicia Supercomputing Center ([CESGA](https://www.cesga.es/en/home-2/)), using 5 nodes with 2 GPUs NVIDIA A100 each one.
 
 ## Evaluation
 In process...