Dataset Viewer
Auto-converted to Parquet Duplicate
messages
listlengths
14
14
[ { "content": "Given a piece of text, determine the main emotion portrayed.\nHe seemed crestfallen after hearing the news.", "role": "user" }, { "content": "Based on the text provided, the main emotion portrayed is \"sadness\" or \"disappointment.\" The word \"crestfallen\" suggests a feeling of bein...
[ { "content": "Given a piece of text, determine the main emotion portrayed.\nHe seemed crestfallen after hearing the news.", "role": "user" }, { "content": "Based on the text provided, the main emotion portrayed is \"sadness\" or \"disappointment.\" The word \"crestfallen\" suggests a feeling of bein...
[ { "content": "Given a piece of text, determine the main emotion portrayed.\nHe seemed crestfallen after hearing the news.", "role": "user" }, { "content": "Based on the text provided, the main emotion portrayed is \"sadness\" or \"disappointment.\" The word \"crestfallen\" suggests a feeling of bein...
[ { "content": "What are the key factors to consider when creating a 3D model of a building or structure? Provide a detailed, multi-step process for the creation of a 3D model, including potential errors or issues that could occur during the process and how to troubleshoot them. Additionally, suggest ways to opti...
[ { "content": "What are the key factors to consider when creating a 3D model of a building or structure? Provide a detailed, multi-step process for the creation of a 3D model, including potential errors or issues that could occur during the process and how to troubleshoot them. Additionally, suggest ways to opti...
[ { "content": "What are the key factors to consider when creating a 3D model of a building or structure? Provide a detailed, multi-step process for the creation of a 3D model, including potential errors or issues that could occur during the process and how to troubleshoot them. Additionally, suggest ways to opti...
[ { "content": "Design a CSS-styled responsive HTML page that incorporates a dynamic survey form. The form should include validated input fields for gathering user's name, age, favorite book, email address, and favorite color. \n\nAdditionally, implement the following:\n\n1. Include placeholder text in each input...
[ { "content": "Design a CSS-styled responsive HTML page that incorporates a dynamic survey form. The form should include validated input fields for gathering user's name, age, favorite book, email address, and favorite color. \n\nAdditionally, implement the following:\n\n1. Include placeholder text in each input...
[ { "content": "Design a CSS-styled responsive HTML page that incorporates a dynamic survey form. The form should include validated input fields for gathering user's name, age, favorite book, email address, and favorite color. \n\nAdditionally, implement the following:\n\n1. Include placeholder text in each input...
[ { "content": "Develop a web page with HTML, CSS, and JavaScript that incorporates a unique animated header and a responsive button. Also, include an error handling system for the button that if it fails to respond, it should display a proper error message without breaking the entire script.\n\nThe twist is, par...
[ { "content": "Develop a web page with HTML, CSS, and JavaScript that incorporates a unique animated header and a responsive button. Also, include an error handling system for the button that if it fails to respond, it should display a proper error message without breaking the entire script.\n\nThe twist is, par...
[ { "content": "Develop a web page with HTML, CSS, and JavaScript that incorporates a unique animated header and a responsive button. Also, include an error handling system for the button that if it fails to respond, it should display a proper error message without breaking the entire script.\n\nThe twist is, par...
[ { "content": "Create a JSON object to list the nutritional content of a plant-based protein alternative. Use the following keys for each nutrient: 'calories', 'protein', 'carbohydrates', 'fats', 'fiber', 'sugars', 'sodium', 'iron', 'calcium', and 'vitamin_B12'. Ensure each nutrient value is listed under its cor...
[ { "content": "Create a JSON object to list the nutritional content of a plant-based protein alternative. Use the following keys for each nutrient: 'calories', 'protein', 'carbohydrates', 'fats', 'fiber', 'sugars', 'sodium', 'iron', 'calcium', and 'vitamin_B12'. Ensure each nutrient value is listed under its cor...
[ { "content": "Create a JSON object to list the nutritional content of a plant-based protein alternative. Use the following keys for each nutrient: 'calories', 'protein', 'carbohydrates', 'fats', 'fiber', 'sugars', 'sodium', 'iron', 'calcium', and 'vitamin_B12'. Ensure each nutrient value is listed under its cor...
[ { "content": "A coal miner's daughter, passionate about sustainable energy, is analyzing the transition from coal-based power to solar power in her town. The town currently generates 1000 MWh of electricity daily from coal. She proposes a model where the town can replace coal with solar power incrementally by i...
[ { "content": "A coal miner's daughter, passionate about sustainable energy, is analyzing the transition from coal-based power to solar power in her town. The town currently generates 1000 MWh of electricity daily from coal. She proposes a model where the town can replace coal with solar power incrementally by i...
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': 143000,
 'dataset_mixer_list': ['VGraf/no_safety_tulu_pref', '160000'],
 'dataset_shuffle_seed': 42,
 'dataset_splits': ['train', 'train'],
 'dataset_start_idx': 142500,
 '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': 7,
 'push_to_hub': True,
 'revision': 'main',
 'revision2': 'main',
 'save_filename': '/weka/oe-adapt-default/victoriag/synth_data/self-talk/clarify_persona_500samples_7turns_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': 3,
 'response_length': 2048,
 'temperature': 1.0,
 'tensor_parallel_size': 1,
 'top_p': 0.9}

Reproduce this dataset

  1. Download the ['generation_multi.py', 'clarify_persona_500samples_7turns_2completions_gpt3.5_gpt3.5_tulupref.jsonl'] from the https://huggingface.co/datasets/VGraf/generation_multi_1746755132.
  2. 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 142500 --dataset_end_idx 143000 --num_turns 7 --num_completions 3 --include_persona --user_type clarify --save_filename /weka/oe-adapt-default/victoriag/synth_data/self-talk/clarify_persona_500samples_7turns_2completions_gpt3.5_gpt3.5_tulupref.jsonl --sanity_check --push_to_hub --temperature 1.0
Downloads last month
3