messages listlengths 16 16 |
|---|
[
{
"content": "Write a detailed paper on whether humans are actually animals.",
"role": "user"
},
{
"content": "Humans are indeed classified as animals within the scientific classification system. This categorization is based on biological similarities and characteristics shared with other members of... |
[
{
"content": "Write a detailed paper on whether humans are actually animals.",
"role": "user"
},
{
"content": "Humans are indeed classified as animals within the scientific classification system. This categorization is based on biological similarities and characteristics shared with other members of... |
[
{
"content": "Write a detailed paper on whether humans are actually animals.",
"role": "user"
},
{
"content": "Humans are indeed classified as animals within the scientific classification system. This categorization is based on biological similarities and characteristics shared with other members of... |
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': 147000,
'dataset_mixer_list': ['VGraf/no_safety_tulu_pref', '160000'],
'dataset_shuffle_seed': 42,
'dataset_splits': ['train', 'train'],
'dataset_start_idx': 146500,
'hf_entity': 'VGraf',
'hf_repo_id': 'generation_multi',
'include_persona': True,
'max_qs': 8,
'mode': 'generation',
'model2_name_or_path': 'gpt-3.5-turbo-0125',
'model_name_or_path': 'gpt-3.5-turbo-0125',
'mt_token_cutoff': 8000,
'num_turns': 8,
'push_to_hub': True,
'revision': 'main',
'revision2': 'main',
'save_filename': '/weka/oe-adapt-default/victoriag/synth_data/self-talk/amend_persona_500samples_8turns_2completions_gpt3.5_gpt3.5_tulupref.jsonl',
'skill': 'chat',
'user_type': 'amend'}
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': 3,
'response_length': 2048,
'temperature': 1.0,
'tensor_parallel_size': 1,
'top_p': 0.9}
Reproduce this dataset
- Download the
['generation_multi.py', 'amend_persona_500samples_8turns_2completions_gpt3.5_gpt3.5_tulupref.jsonl']from the https://huggingface.co/datasets/VGraf/generation_multi_1746755451. - Run
python open_instruct/rejection_sampling/generation_multi.py --dataset_mixer_list VGraf/no_safety_tulu_pref 160000 --dataset_splits train train --model_name_or_path gpt-3.5-turbo-0125 --model2_name_or_path gpt-3.5-turbo-0125 --dataset_shuffle_seed 42 --dataset_start_idx 146500 --dataset_end_idx 147000 --num_turns 8 --num_completions 3 --include_persona --user_type amend --save_filename /weka/oe-adapt-default/victoriag/synth_data/self-talk/amend_persona_500samples_8turns_2completions_gpt3.5_gpt3.5_tulupref.jsonl --sanity_check --push_to_hub --temperature 1.0
- Downloads last month
- 4