messages listlengths 8 8 |
|---|
[
{
"content": "ciao chat, vorrei che tu mi scrivessi meglio questo e lo rendessi più lungo. \"Bette scese dall’auto, bofonchiando e borbottando mentre con attenzione cercava di non scivolare sul leggero strato di neve fresca che colorava il cemento del parcheggio, circumnavigando l’auto per raggiungere il bagagl... |
[
{
"content": "ciao chat, vorrei che tu mi scrivessi meglio questo e lo rendessi più lungo. \"Bette scese dall’auto, bofonchiando e borbottando mentre con attenzione cercava di non scivolare sul leggero strato di neve fresca che colorava il cemento del parcheggio, circumnavigando l’auto per raggiungere il bagagl... |
[
{
"content": "ciao chat, vorrei che tu mi scrivessi meglio questo e lo rendessi più lungo. \"Bette scese dall’auto, bofonchiando e borbottando mentre con attenzione cercava di non scivolare sul leggero strato di neve fresca che colorava il cemento del parcheggio, circumnavigando l’auto per raggiungere il bagagl... |
[
{
"content": "In this task, you will be presented with an English sentence, and you have to translate it into Arabic.\n\n[Q]: I felt compelled to do something, so I painted him.\n[A]: شعرت بالرغبة في القيام بشيء ما، لذلك رسمته.\n\n\n[Q]: I tagged him. I made the tag, but I dropped the ball.\n[A]: لقد لحقت به لك... |
[
{
"content": "In this task, you will be presented with an English sentence, and you have to translate it into Arabic.\n\n[Q]: I felt compelled to do something, so I painted him.\n[A]: شعرت بالرغبة في القيام بشيء ما، لذلك رسمته.\n\n\n[Q]: I tagged him. I made the tag, but I dropped the ball.\n[A]: لقد لحقت به لك... |
[
{
"content": "In this task, you will be presented with an English sentence, and you have to translate it into Arabic.\n\n[Q]: I felt compelled to do something, so I painted him.\n[A]: شعرت بالرغبة في القيام بشيء ما، لذلك رسمته.\n\n\n[Q]: I tagged him. I made the tag, but I dropped the ball.\n[A]: لقد لحقت به لك... |
[
{
"content": "Compose a ballad using the following words while maintaining a consistent rhyme scheme and meter:\n- ember\n- glisten\n- solace\n- peril\n- sanctuary \nThe ballad must have a meter of 8-6-8-6 syllables per stanza and an ABAB rhyme scheme.\nHere's an example stanza using the given words:\nThe ember... |
[
{
"content": "Compose a ballad using the following words while maintaining a consistent rhyme scheme and meter:\n- ember\n- glisten\n- solace\n- peril\n- sanctuary \nThe ballad must have a meter of 8-6-8-6 syllables per stanza and an ABAB rhyme scheme.\nHere's an example stanza using the given words:\nThe ember... |
[
{
"content": "Compose a ballad using the following words while maintaining a consistent rhyme scheme and meter:\n- ember\n- glisten\n- solace\n- peril\n- sanctuary \nThe ballad must have a meter of 8-6-8-6 syllables per stanza and an ABAB rhyme scheme.\nHere's an example stanza using the given words:\nThe ember... |
[
{
"content": "Гельминтозы у детей. Критерии эффективности лечения.",
"role": "user"
},
{
"content": "Гельминтозы у детей - это группа заболеваний, вызванных паразитическими червями. Критерии эффективности лечения гельминтозов включают снижение количества паразитов в организме, улучшение клинических... |
[
{
"content": "Гельминтозы у детей. Критерии эффективности лечения.",
"role": "user"
},
{
"content": "Гельминтозы у детей - это группа заболеваний, вызванных паразитическими червями. Критерии эффективности лечения гельминтозов включают снижение количества паразитов в организме, улучшение клинических... |
[
{
"content": "Гельминтозы у детей. Критерии эффективности лечения.",
"role": "user"
},
{
"content": "Гельминтозы у детей - это группа заболеваний, вызванных паразитическими червями. Критерии эффективности лечения гельминтозов включают снижение количества паразитов в организме, улучшение клинических... |
[
{
"content": "Respond in a funny, sarcastic manner to this text, pointing put the fallacies: And you still are having really bad takes thinking G5 is better than G4. The G5 movie gave us hope, the series removed that hope, and it’s been downhill ever since. There’s nothing to use anymore to say “it’ll get bette... |
[
{
"content": "Respond in a funny, sarcastic manner to this text, pointing put the fallacies: And you still are having really bad takes thinking G5 is better than G4. The G5 movie gave us hope, the series removed that hope, and it’s been downhill ever since. There’s nothing to use anymore to say “it’ll get bette... |
[
{
"content": "Respond in a funny, sarcastic manner to this text, pointing put the fallacies: And you still are having really bad takes thinking G5 is better than G4. The G5 movie gave us hope, the series removed that hope, and it’s been downhill ever since. There’s nothing to use anymore to say “it’ll get bette... |
[
{
"content": "IN: French:\n\nThe Commission’s services look to apply objectively the same conditions to the subvention contracts of the ECIP programme.\nOUT: Les services de la Commission veillent à appliquer objectivement les mêmes conditions à l’ensemble des contrats de subvention du programme ECIP.\nIN: Fren... |
[
{
"content": "IN: French:\n\nThe Commission’s services look to apply objectively the same conditions to the subvention contracts of the ECIP programme.\nOUT: Les services de la Commission veillent à appliquer objectivement les mêmes conditions à l’ensemble des contrats de subvention du programme ECIP.\nIN: Fren... |
[
{
"content": "IN: French:\n\nThe Commission’s services look to apply objectively the same conditions to the subvention contracts of the ECIP programme.\nOUT: Les services de la Commission veillent à appliquer objectivement les mêmes conditions à l’ensemble des contrats de subvention du programme ECIP.\nIN: Fren... |
[
{
"content": "A cybersecurity professional is analyzing a system for vulnerabilities and is particularly concerned about buffer overflows. The system under analysis processes data in packets of varying sizes, and the professional is tasked with modeling the likelihood of buffer overflow incidents.\n\nConsider t... |
[
{
"content": "A cybersecurity professional is analyzing a system for vulnerabilities and is particularly concerned about buffer overflows. The system under analysis processes data in packets of varying sizes, and the professional is tasked with modeling the likelihood of buffer overflow incidents.\n\nConsider t... |
[
{
"content": "A cybersecurity professional is analyzing a system for vulnerabilities and is particularly concerned about buffer overflows. The system under analysis processes data in packets of varying sizes, and the professional is tasked with modeling the likelihood of buffer overflow incidents.\n\nConsider t... |
[
{
"content": "What happens if you trip while playing basketball? - sweat - dribbling - hurt yourself - fall down - make baskets The best answer is\n From Answer with one of the following options: a), b), c), d)",
"role": "user"
},
{
"content": "Based on the given factors - sweat, dribbling, hurt yo... |
[
{
"content": "What happens if you trip while playing basketball? - sweat - dribbling - hurt yourself - fall down - make baskets The best answer is\n From Answer with one of the following options: a), b), c), d)",
"role": "user"
},
{
"content": "Based on the given factors - sweat, dribbling, hurt yo... |
[
{
"content": "What happens if you trip while playing basketball? - sweat - dribbling - hurt yourself - fall down - make baskets The best answer is\n From Answer with one of the following options: a), b), c), d)",
"role": "user"
},
{
"content": "Based on the given factors - sweat, dribbling, hurt yo... |
[
{
"content": "Can we conclude from \"A race dog leaps a large stride as others follow behind.\" that \"The dog is rolling on the ground.\"?\nOptions:\n- yes\n- no\n- it is not possible to tell A step-by-step solution is:\n Your entire response should be in English, and in all lowercase letters. No capital lette... |
[
{
"content": "Can we conclude from \"A race dog leaps a large stride as others follow behind.\" that \"The dog is rolling on the ground.\"?\nOptions:\n- yes\n- no\n- it is not possible to tell A step-by-step solution is:\n Your entire response should be in English, and in all lowercase letters. No capital lette... |
[
{
"content": "Can we conclude from \"A race dog leaps a large stride as others follow behind.\" that \"The dog is rolling on the ground.\"?\nOptions:\n- yes\n- no\n- it is not possible to tell A step-by-step solution is:\n Your entire response should be in English, and in all lowercase letters. No capital lette... |
[
{
"content": "TASK DEFINITION: In this task, given a sentence in the Vietnamese language, your task is to convert it into the English language.\nPROBLEM: Tuy nhiên, Ross Brawn tỏ ra nhiệt tình muốn giữ lại Briton và cả tay đua người Brazil Rubens Barrichello hoặc kí hợp đồng với tay đua Bruno Senna của đường đu... |
[
{
"content": "TASK DEFINITION: In this task, given a sentence in the Vietnamese language, your task is to convert it into the English language.\nPROBLEM: Tuy nhiên, Ross Brawn tỏ ra nhiệt tình muốn giữ lại Briton và cả tay đua người Brazil Rubens Barrichello hoặc kí hợp đồng với tay đua Bruno Senna của đường đu... |
[
{
"content": "TASK DEFINITION: In this task, given a sentence in the Vietnamese language, your task is to convert it into the English language.\nPROBLEM: Tuy nhiên, Ross Brawn tỏ ra nhiệt tình muốn giữ lại Briton và cả tay đua người Brazil Rubens Barrichello hoặc kí hợp đồng với tay đua Bruno Senna của đường đu... |
End of preview. Expand in Data Studio
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': 145000,
'dataset_mixer_list': ['VGraf/no_safety_tulu_pref', '160000'],
'dataset_shuffle_seed': 42,
'dataset_splits': ['train', 'train'],
'dataset_start_idx': 144500,
'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': 4,
'push_to_hub': True,
'revision': 'main',
'revision2': 'main',
'save_filename': '/weka/oe-adapt-default/victoriag/synth_data/self-talk/amend_persona_500samples_4turns_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_4turns_2completions_gpt3.5_gpt3.5_tulupref.jsonl']from the https://huggingface.co/datasets/VGraf/generation_multi_1746754677. - 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 144500 --dataset_end_idx 145000 --num_turns 4 --num_completions 3 --include_persona --user_type amend --save_filename /weka/oe-adapt-default/victoriag/synth_data/self-talk/amend_persona_500samples_4turns_2completions_gpt3.5_gpt3.5_tulupref.jsonl --sanity_check --push_to_hub --temperature 1.0
- Downloads last month
- 4