Use Alpaca template with Phi-3

[eugeniosegala]

Hello!

Is there a way to use the Alpaca template with Phi-3?

I'm struggling a bit to understand the documentation, I was wondering if anyone can help me understand how to use it here and define the proper mapping:

from unsloth.chat_templates import get_chat_template

tokenizer = get_chat_template(
    tokenizer,
    chat_template = "phi-3", # Supports zephyr, chatml, mistral, llama, alpaca, vicuna, vicuna_old, unsloth
    mapping = {"role" : "from", "content" : "value", "user" : "human", "assistant" : "gpt"}, # ShareGPT style
)

def formatting_prompts_func(examples):
    convos = examples["conversations"]
    texts = [tokenizer.apply_chat_template(convo, tokenize = False, add_generation_prompt = False) for convo in convos]
    return { "text" : texts, }
pass

from datasets import load_dataset
dataset = load_dataset("philschmid/guanaco-sharegpt-style", split = "train")
dataset = dataset.map(formatting_prompts_func, batched = True,)

Also, a few days ago the Phi-3 Colab notebook was different and it seemed to be using the alpaca template, why did it change?