messages listlengths 2 2 |
|---|
[
{
"content": "Can you tell me how to format an url in rst?",
"role": "user"
},
{
"content": "Q:\nQ:\nQ:\nQ:\nQ:\nQ:\nQ:",
"role": "assistant"
}
] |
[
{
"content": "I would like you to act as a virtual assistant, I will give you commands and you will execute them automatically for me.\nPlease only reply in the following formats, only replace the content inside the curly braces with the relevant category\n\nWhen you require additional information:\n[ADDITIONAL... |
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/alpaca_remainder2', '1.0'],
'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/alpacaeval_related_prompts_remainder.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', 'alpacaeval_related_prompts_remainder.jsonl']from the https://huggingface.co/datasets/VGraf/generation_multi_1768282235. - Run
python open_instruct/rejection_sampling/generation_multi.py --dataset_mixer_list VGraf/alpaca_remainder2 1.0 --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/alpacaeval_related_prompts_remainder.jsonl --sanity_check --push_to_hub
- Downloads last month
- 7