Dataset Viewer
Auto-converted to Parquet Duplicate
messages
listlengths
10
10
[ { "content": "How can I implement a system in PHP that estimates the state of the system with noisy measurements using a Kalman filter? The system is described by the following equations:\nx[k+1] = Ax[k] + Bu[k] + w[k]\ny[k] = Cx[k] + v[k]\nWhere x[k] is the state vector, u[k] is the control input, y[k] is the ...
[ { "content": "How can I implement a system in PHP that estimates the state of the system with noisy measurements using a Kalman filter? The system is described by the following equations:\nx[k+1] = Ax[k] + Bu[k] + w[k]\ny[k] = Cx[k] + v[k]\nWhere x[k] is the state vector, u[k] is the control input, y[k] is the ...
[ { "content": "Podrías hacerme un post de Instagram de 200 palabras, siendo un resumen de la primera guerra mundial y con 15 hastag relacionados. Gracias.", "role": "user" }, { "content": "¡Claro que sí! Aquí tienes un post de Instagram sobre la Primera Guerra Mundial:\n\n\"Hace un siglo, el mundo se...
[ { "content": "Podrías hacerme un post de Instagram de 200 palabras, siendo un resumen de la primera guerra mundial y con 15 hastag relacionados. Gracias.", "role": "user" }, { "content": "¡Claro que sí! Aquí tienes un post de Instagram sobre la Primera Guerra Mundial:\n\n\"Hace un siglo, el mundo se...
[ { "content": "Today, I paid a visit to the Alchemy Festival at the Southbank Centre, a two week celebration of music, dance, film and performance from India, the UK and South Asia. Starting inside, the contemporary, plain interior of the foyer was given an injection of colour with saris and multi-coloured blank...
[ { "content": "Today, I paid a visit to the Alchemy Festival at the Southbank Centre, a two week celebration of music, dance, film and performance from India, the UK and South Asia. Starting inside, the contemporary, plain interior of the foyer was given an injection of colour with saris and multi-coloured blank...
[ { "content": "A woman texted : Hiya ^^” I saw your post and I was curious…You sound like you could be a nice person so I sent you a chat message. I’m 22F also in Europe and I like to play games and exercise too! (write a reply to have back and forth conversation instead of it feeling like an interview)", "r...
[ { "content": "A woman texted : Hiya ^^” I saw your post and I was curious…You sound like you could be a nice person so I sent you a chat message. I’m 22F also in Europe and I like to play games and exercise too! (write a reply to have back and forth conversation instead of it feeling like an interview)", "r...
[ { "content": "Answer with at least 3 sentences. First question: How many months does it require to prepare for the CAT?\nSecond question: How many months does it take to prepare for the CAT exam?\nAre these two questions asking the same thing?\n\nI. no\nII. yes", "role": "user" }, { "content": "The ...
[ { "content": "Answer with at least 3 sentences. First question: How many months does it require to prepare for the CAT?\nSecond question: How many months does it take to prepare for the CAT exam?\nAre these two questions asking the same thing?\n\nI. no\nII. yes", "role": "user" }, { "content": "The ...
[ { "content": "You are given a sentence in Spanish. Your job is to translate the Spanish sentence into Galician.\nExample: Gracias.\nExample solution: Grazas.\nExample explanation: The Spanish sentence is correctly translated into Galician, because the meaning is preserved.\n\nProblem: Por ejemplo, en junio de 2...
[ { "content": "You are given a sentence in Spanish. Your job is to translate the Spanish sentence into Galician.\nExample: Gracias.\nExample solution: Grazas.\nExample explanation: The Spanish sentence is correctly translated into Galician, because the meaning is preserved.\n\nProblem: Por ejemplo, en junio de 2...
[ { "content": "WRITE A LETTER TO MR. WILLIAM LOREN EXPRESSING YOUR GRATITUDE FOR HIS FRIENDSHIP OVER THE YEARS. MENTION SPECIFIC MEMORIES OR EVENTS THAT HAVE SOLIDIFIED YOUR BOND. MAKE SURE TO INCLUDE AT LEAST THREE PARAGRAPHS, ALL IN ENGLISH AND LOWERCASE.", "role": "user" }, { "content": "Dear mr. ...
[ { "content": "WRITE A LETTER TO MR. WILLIAM LOREN EXPRESSING YOUR GRATITUDE FOR HIS FRIENDSHIP OVER THE YEARS. MENTION SPECIFIC MEMORIES OR EVENTS THAT HAVE SOLIDIFIED YOUR BOND. MAKE SURE TO INCLUDE AT LEAST THREE PARAGRAPHS, ALL IN ENGLISH AND LOWERCASE.", "role": "user" }, { "content": "Dear mr. ...
[ { "content": "Provide three tips for incorporating mindfulness into a stylish lifestyle without using any commas and limit the response to four sentences.", "role": "user" }, { "content": "1. Infuse mindfulness in fashion choices by selecting pieces that reflect your true essence and values. 2. Embr...
[ { "content": "Provide three tips for incorporating mindfulness into a stylish lifestyle without using any commas and limit the response to four sentences.", "role": "user" }, { "content": "1. Infuse mindfulness in fashion choices by selecting pieces that reflect your true essence and values. 2. Embr...
[ { "content": "There should be 28 paragraphs. Paragraphs and only paragraphs are separated with each other by two line breaks. The 14-th paragraph must start with word {first word}. Ques:Title: Wii Review: I purchased the Wii from Amazon.com and I love it. The purchase process was very efficient and the product ...
[ { "content": "There should be 28 paragraphs. Paragraphs and only paragraphs are separated with each other by two line breaks. The 14-th paragraph must start with word {first word}. Ques:Title: Wii Review: I purchased the Wii from Amazon.com and I love it. The purchase process was very efficient and the product ...

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': 142000,
 'dataset_mixer_list': ['VGraf/no_safety_tulu_pref', '150000'],
 'dataset_shuffle_seed': 42,
 'dataset_splits': ['train', 'train'],
 'dataset_start_idx': 141500,
 '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': 5,
 'push_to_hub': True,
 'revision': 'main',
 'revision2': 'main',
 'save_filename': '/weka/oe-adapt-default/victoriag/synth_data/self-talk/clarify_persona_500samples_5turns_2completions_gpt3.5_gpt3.5_tulupref.jsonl',
 'skill': 'chat',
 'user_type': 'clarify'}

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': 2,
 'response_length': 2048,
 'temperature': 0.8,
 'tensor_parallel_size': 1,
 'top_p': 0.9}

Reproduce this dataset

  1. Download the ['generation_multi.py', 'clarify_persona_500samples_5turns_2completions_gpt3.5_gpt3.5_tulupref.jsonl'] from the https://huggingface.co/datasets/VGraf/generation_multi_1746751666.
  2. Run python open_instruct/rejection_sampling/generation_multi.py --dataset_mixer_list VGraf/no_safety_tulu_pref 150000 --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 141500 --dataset_end_idx 142000 --num_turns 5 --num_completions 2 --include_persona --user_type clarify --save_filename /weka/oe-adapt-default/victoriag/synth_data/self-talk/clarify_persona_500samples_5turns_2completions_gpt3.5_gpt3.5_tulupref.jsonl --sanity_check --push_to_hub --temperature 0.8
Downloads last month
4