messages listlengths 2 2 |
|---|
[
{
"content": "You will be given a definition of a task first, then some input of the task.\nGiven a premise, an initial context, an original ending, and a new ending, the task is to generate the counterfactual context that is aligned with the new ending. Each instance consists of a five-sentence story. The premise is the first sentence of a story, and the second sentence, which is the initial context, provides more information about the story's context. The original ending is the last three sentences of the story. Also, you are given a new ending that can provide the new story with the same premise. You should write a counterfactual context to explain the small differences between the original and new endings. More specifically, a story context contains the general plot of the story. And a counterfactual context is a slight modification to the initial context. To sum up, you should write the second sentence of a story based on the premise(first sentence) and the new ending(last three sentences) of the story.\n\nPremise: Beth sent a letter to Santa Claus. \n Initial Context: She received a letter back in the mail. \n Original Ending: Beth did not think that it sounded like the real Santa. She sent another letter calling that Santa a fake. She did not receive another letter back in the mail. \n New ending: Beth now thinks that Santa is not real. She sent letters to the neighborhood letting them know Santa is fake. She received many angry letters from parents in the mail. \nOutput:",
"role": "user"
},
{
"content": "Q:\nWhat is the concept of counterfactual context in storytelling?\nQ:\nHow do you generate a counterfactual context aligned with a new story ending?\nQ:\nWhat is the purpose of writing a counterfactual context in storytelling?\nQ:\nHow can a slight modification to the initial context affect the storytelling outcome?\nQ:\nWhy is it important to maintain consistency between the premise and the new ending in a story context?",
"role": "assistant"
}
] |
[
{
"content": "Generate a single sentence summary given the following text.\n\nAdditional Context:\nA study conducted in 2020 shows that online education is becoming more and more popular for students. As students make the transition from traditional education to online courses, they gain more flexibility and access to innovative learning opportunities.\n\nAnswer: In your entire response, refrain from the use of any commas.",
"role": "user"
},
{
"content": "Q:\nQ:\nQ:\nQ:\nQ:\nQ:",
"role": "assistant"
}
] |
allenai/open_instruct: Generation Dataset
See https://github.com/allenai/open-instruct/blob/main/docs/algorithms/rejection_sampling.md for more detail
Configs
args:
{'add_timestamp': True,
'dataset_end_idx': 2,
'dataset_mixer_list': ['VGraf/no_safety_tulu_pref', '2'],
'dataset_shuffle': True,
'dataset_splits': ['train', 'train'],
'dataset_start_idx': 0,
'hf_entity': 'VGraf',
'hf_repo_id': 'generation_multi',
'include_persona': False,
'max_qs': 7,
'mode': 'generation',
'model2_name_or_path': 'cleanrl/EleutherAI_pythia-6.9b-deduped__sft__tldr',
'model_name_or_path': 'gpt-3.5-turbo-0125',
'mt_token_cutoff': 8000,
'num_turns': 1,
'push_to_hub': True,
'revision': 'main',
'revision2': 'main',
'save_filename': '/weka/oe-adapt-default/victoriag/synth_data/nonsafety_pref_related_prompts.jsonl',
'skill': 'related_prompts',
'user_type': 'follow-up'}
dataset_config:
{'batched': False,
'binary_messages_key': 'messages',
'chat_template': 'simple_chat',
'convert_preference_to_binary_dataset': False,
'label': 'binary_labels',
'load_from_cache_file': False,
'max_prompt_token_lenth': None,
'max_token_length': None,
'ncols': 2,
'num_proc': 1,
'preference_chosen_key': 'chosen',
'preference_rejected_key': 'rejected',
'sanity_check': True,
'sanity_check_max_samples': 100,
'sft_messages_key': 'messages',
'train_only_on_prompt': False}
gen_args:
{'num_completions': 1,
'response_length': 2048,
'temperature': 0.8,
'tensor_parallel_size': 1,
'top_p': 0.9}
Reproduce this dataset
- Download the
['generation_multi.py', 'nonsafety_pref_related_prompts.jsonl']from the https://huggingface.co/datasets/VGraf/generation_multi_1742346269. - Run
python open_instruct/rejection_sampling/generation_multi.py --dataset_mixer_list VGraf/no_safety_tulu_pref 2 --dataset_splits train train --model_name_or_path gpt-3.5-turbo-0125 --num_completions 1 --dataset_shuffle --max_qs 7 --skill related_prompts --save_filename /weka/oe-adapt-default/victoriag/synth_data/nonsafety_pref_related_prompts.jsonl --sanity_check --push_to_hub
- Downloads last month
- 5