Update README.md

README.md

@@ -10,7 +10,32 @@ pipeline_tag: text-generation
 ## Llama 2-13b-alpaca-spanish LoRA
 This is a LoRA for Llama 2 13B trained on a translated [alpaca dataset](https://huggingface.co/datasets/bertin-project/alpaca-spanish) on an attempt to improve spanish performance of the Llama-2 foundation model with a conversational focus.
 
-Base model used was [The Bloke's Llama-2-13B-fp16](https://huggingface.co/TheBloke/Llama-2-13B-fp16) trained in 4bit precision.
+Base model used was [The Bloke's Llama-2-13B-fp16](https://huggingface.co/TheBloke/Llama-2-13B-fp16) trained in 4bit precision with an added padding token.
+
+## Important INFO
+The original Llama 2 model does not have a padding token, this came to be restrictive for training for me. To adress this, I added a padding token to the tokenizer associated with the model.
+```python
+from transformers import LlamaTokenizer, LlamaForCausalLM
+
+model_name = 'TheBloke/Llama-2-13B-fp16'
+
+model = LlamaForCausalLM.from_pretrained(model_name).half()
+tokenizer = LlamaTokenizer.from_pretrained(model_name)
+
+# Add padding token
+tokenizer.add_tokens(['<PAD>'])
+tokenizer.pad_token = '<PAD>'
+
+# Resizing the model
+model.resize_token_embeddings(len(tokenizer))
+
+padded_model_name = 'Llama-2-13B-fp16-padded'
+
+# Save
+tokenizer.save_pretrained(padded_model_name)
+model.save_pretrained(padded_model_name)
+
+```
 
 | Training parameteres      |   |
 | ----------- | ----------- |