Llama-Guard / toxicchat_dataset.py
taozi555's picture
Upload toxicchat_dataset.py
f2676f8 verified
# Copyright (c) Meta Platforms, Inc. and affiliates.
# This software may be used and distributed according to the terms of the Llama 3.1 Community License Agreement.
# For dataset details visit: https://huggingface.co/datasets/lmsys/toxic-chat
import copy
import datasets
import itertools
from llama_recipes.inference.prompt_format_utils import LLAMA_GUARD_3_CATEGORY
import ast
import fire
def tokenize_prompt_and_labels(full_prompt, tokenizer):
prompt_tokens = tokenizer.encode(full_prompt)
combined_tokens = {
"input_ids": list(prompt_tokens),
"labels": list(prompt_tokens)
}
return dict(combined_tokens, attention_mask=[1]*len(combined_tokens["input_ids"]))
from llama_recipes.data.llama_guard.finetuning_data_formatter import TrainingExample, Guidelines, Category, LlamaGuardPromptConfigs, LlamaGuardGenerationConfigs, ExplanationPosition, AugmentationConfigs, FormatterConfigs, create_formatted_finetuning_examples
from datasets import Dataset, DatasetInfo
def mapTcCategoriesToLGCategories(TcCategoriesString):
TcCategories = ast.literal_eval(TcCategoriesString)
if(len(TcCategories)==0):
return None
ranked = sorted(TcCategories, key=lambda x: x[1], reverse=True)
primary = ranked[0][0] if len(ranked) else None
TcMapping = {
"S12":"012",
"violence":"01",
"sexual/minors":"04",
"self-harm/intent":"011",
"hate":"010",
"harassment":"010",
"self-harm":"011",
"self-harm/instructions":"011",
"violence/graphic":"01",
"harassment/threatening":"010",
"hate/threatening":"010"
}
return TcMapping[primary]
def get_llamaguard_toxicchat_dataset(dataset_config, tokenizer, split, return_jsonl=False):
dataset = datasets.load_dataset('json', data_files="/root/autodl-tmp/transformed_data.json", split='train')
if return_jsonl:
jsonl_data = [];
for x in dataset.to_iterable_dataset():
jsonl_data.append({
"prompt":x['prompt'],
"generation":x['response'],
"label":("good" if x['label'] == "safe" else "bad"),
"unsafe_content": [] if x["label"]=="safe" else ["012"]
})
return jsonl_data
guidelines = Guidelines(
categories=LLAMA_GUARD_3_CATEGORY,
category_code_prefix="O")
# Setting up configs
llama_guard_prompt_configs = LlamaGuardPromptConfigs(
instructions_format_string="""<|begin_of_text|><|start_header_id|>user<|end_header_id|> Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
{guidelines}
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
{conversation}
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. <|eot_id|><|start_header_id|>assistant<|end_header_id|>""",
should_include_category_descriptions=False,
should_shuffle_category_codes=False
)
llama_guard_generation_configs = LlamaGuardGenerationConfigs(
should_list_violated_codes=True,
explanation_position=None
)
augmentation_configs = AugmentationConfigs(
should_add_examples_with_dropped_nonviolated_prompt_categories=False,
should_add_examples_with_dropped_violated_and_nonviolated_prompt_categories=False,
explanation_for_augmentation_with_dropped_violated_and_nonviolated_prompt_categories="Response is safe because any riskiness in it is related to categories we're not trying to detect."
)
formatter_configs = FormatterConfigs(
guidelines=guidelines,
llama_guard_prompt_configs=llama_guard_prompt_configs,
llama_guard_generation_configs=llama_guard_generation_configs,
augmentation_configs=augmentation_configs,
random_seed=42
)
dataset = dataset.map(lambda x: {"full_prompt": create_formatted_finetuning_examples(
[TrainingExample(
prompt=x["prompt"],
response=None,
violated_category_codes = [] if x["label"]=="safe" else ["012"],
label=x["label"],
explanation=x["explanation"]
)],
formatter_configs)[0]},
remove_columns=list(dataset.features))
dataset = dataset.map(lambda x: tokenize_prompt_and_labels(x["full_prompt"], tokenizer), remove_columns=list(dataset.features))
return dataset
def main(return_jsonl = False):
from transformers import AutoTokenizer
model_id: str = "/home/ubuntu/LG3-interim-hf-weights"
tokenizer = AutoTokenizer.from_pretrained(model_id)
if return_jsonl:
dataset = get_llamaguard_toxicchat_dataset(None, tokenizer, "train", return_jsonl = True)
print(dataset[0:50])
else:
dataset = get_llamaguard_toxicchat_dataset(None, tokenizer, "train")
print(dataset[0])
if __name__ == '__main__':
fire.Fire(main)