Chat Data Format for LLMs - Unsloth Templates

#[NOTE] To train only on completions (ignoring the user's input) read TRL's docs here.

#We use our get_chat_template function to get the correct chat template. We support zephyr, chatml, mistral, llama, alpaca, vicuna, vicuna_old and our own optimized unsloth template.

#Normally one has to train <|im_start|> and <|im_end|>. We instead map <|im_end|> to be the EOS token, and leave <|im_start|> as is. This requires no additional training of additional tokens.

#Note ShareGPT uses {"from": "human", "value" : "Hi"} and not {"role": "user", "content" : "Hi"}, so we use mapping to map it.

#For text completions like novel writing, try this notebook.


from unsloth.chat_templates import get_chat_template

tokenizer = get_chat_template(
    tokenizer,
    chat_template = "chatml", # Supports zephyr, chatml, mistral, llama, alpaca, vicuna, vicuna_old, unsloth
    mapping = {"role" : "from", "content" : "value", "user" : "human", "assistant" : "gpt"}, # ShareGPT style
    map_eos_token = True, # Maps <|im_end|> to </s> instead
)

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,)