messages listlengths 16 16 |
|---|
[
{
"content": "Name the location of the 4th fists in our body.",
"role": "user"
},
{
"content": "The fourth fist in our body is located in the lower right quadrant of the abdomen, known as the right lower quadrant (RLQ). This fist is formed by the cecum, appendix, part of the colon, and the right ova... |
[
{
"content": "Name the location of the 4th fists in our body.",
"role": "user"
},
{
"content": "The fourth fist in our body is located in the lower right quadrant of the abdomen, known as the right lower quadrant (RLQ). This fist is formed by the cecum, appendix, part of the colon, and the right ova... |
[
{
"content": "Name the location of the 4th fists in our body.",
"role": "user"
},
{
"content": "The fourth fist in our body is located in the lower right quadrant of the abdomen, known as the right lower quadrant (RLQ). This fist is formed by the cecum, appendix, part of the colon, and the right ova... |
[
{
"content": "A long-time user of Done Deal Pro Forums, who enjoys networking with fellow screenwriters, decides to analyze the growth of their network over time. Let the number of connections they make each month be modeled by the function \\( C(t) = 5t^2 + 3t + 2 \\), where \\( t \\) is the number of months s... |
[
{
"content": "A long-time user of Done Deal Pro Forums, who enjoys networking with fellow screenwriters, decides to analyze the growth of their network over time. Let the number of connections they make each month be modeled by the function \\( C(t) = 5t^2 + 3t + 2 \\), where \\( t \\) is the number of months s... |
[
{
"content": "A long-time user of Done Deal Pro Forums, who enjoys networking with fellow screenwriters, decides to analyze the growth of their network over time. Let the number of connections they make each month be modeled by the function \\( C(t) = 5t^2 + 3t + 2 \\), where \\( t \\) is the number of months s... |
[
{
"content": "如何对嵌入式linux内核裁剪",
"role": "user"
},
{
"content": "对嵌入式Linux内核进行裁剪是一个重要的步骤，可以帮助减小内核的体积并提高性能。裁剪内核可以通过配置内核源代码中的选项来实现，可以使用工具如make menuconfig，make xconfig或make defconfig。在裁剪时，需要注意保留必要的功能和驱动程序，同时去除不必要的模块以减小内核的大小。裁剪过程需要谨慎进行，以确保系统的稳定性和功能完整性。",
"role": "assistant"
},
{
"content": "H... |
[
{
"content": "如何对嵌入式linux内核裁剪",
"role": "user"
},
{
"content": "对嵌入式Linux内核进行裁剪是一个重要的步骤，可以帮助减小内核的体积并提高性能。裁剪内核可以通过配置内核源代码中的选项来实现，可以使用工具如make menuconfig，make xconfig或make defconfig。在裁剪时，需要注意保留必要的功能和驱动程序，同时去除不必要的模块以减小内核的大小。裁剪过程需要谨慎进行，以确保系统的稳定性和功能完整性。",
"role": "assistant"
},
{
"content": "H... |
[
{
"content": "如何对嵌入式linux内核裁剪",
"role": "user"
},
{
"content": "对嵌入式Linux内核进行裁剪是一个重要的步骤，可以帮助减小内核的体积并提高性能。裁剪内核可以通过配置内核源代码中的选项来实现，可以使用工具如make menuconfig，make xconfig或make defconfig。在裁剪时，需要注意保留必要的功能和驱动程序，同时去除不必要的模块以减小内核的大小。裁剪过程需要谨慎进行，以确保系统的稳定性和功能完整性。",
"role": "assistant"
},
{
"content": "H... |
[
{
"content": "Change the following sentence from the singular form to the plural form.\nThe cat is drinking.",
"role": "user"
},
{
"content": "Change the following sentence from the singular form to the plural form.\nThe cats are drinking.",
"role": "assistant"
},
{
"content": "As a scie... |
[
{
"content": "Change the following sentence from the singular form to the plural form.\nThe cat is drinking.",
"role": "user"
},
{
"content": "Change the following sentence from the singular form to the plural form.\nThe cats are drinking.",
"role": "assistant"
},
{
"content": "As a scie... |
[
{
"content": "Change the following sentence from the singular form to the plural form.\nThe cat is drinking.",
"role": "user"
},
{
"content": "Change the following sentence from the singular form to the plural form.\nThe cats are drinking.",
"role": "assistant"
},
{
"content": "As a scie... |
[
{
"content": "Los 5 principios clave de Six Sigma\nLa metodología Six Sigma tiene 5 principios clave que puedes aplicar cuando analices tus procesos.\n\n1. Poner el foco en el cliente\nEn Six Sigma, el objetivo es garantizar que puedes brindar a los clientes el mayor valor posible. Es decir, tu equipo debería d... |
[
{
"content": "Los 5 principios clave de Six Sigma\nLa metodología Six Sigma tiene 5 principios clave que puedes aplicar cuando analices tus procesos.\n\n1. Poner el foco en el cliente\nEn Six Sigma, el objetivo es garantizar que puedes brindar a los clientes el mayor valor posible. Es decir, tu equipo debería d... |
[
{
"content": "Los 5 principios clave de Six Sigma\nLa metodología Six Sigma tiene 5 principios clave que puedes aplicar cuando analices tus procesos.\n\n1. Poner el foco en el cliente\nEn Six Sigma, el objetivo es garantizar que puedes brindar a los clientes el mayor valor posible. Es decir, tu equipo debería d... |
[
{
"content": "GPT-3.5 Chatbot\nThis app provides you full access to GPT-3.5 (4096 token limit). You don't need any OPENAI API key.\nChatbot\nso, we(you english people) using the indian term God and follow a christian religion at the same time?\nYes, many English-speaking people who practice Christianity use the... |
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': 150500,
'dataset_mixer_list': ['VGraf/no_safety_tulu_pref', '160000'],
'dataset_shuffle_seed': 42,
'dataset_splits': ['train', 'train'],
'dataset_start_idx': 150000,
'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/follow-up_persona_500samples_8turns_2completions_gpt3.5_gpt3.5_tulupref.jsonl',
'skill': 'chat',
'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': 3,
'response_length': 2048,
'temperature': 1.0,
'tensor_parallel_size': 1,
'top_p': 0.9}
Reproduce this dataset
- Download the
['generation_multi.py', 'follow-up_persona_500samples_8turns_2completions_gpt3.5_gpt3.5_tulupref.jsonl']from the https://huggingface.co/datasets/VGraf/generation_multi_1746755251. - 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 150000 --dataset_end_idx 150500 --num_turns 8 --num_completions 3 --include_persona --user_type follow-up --save_filename /weka/oe-adapt-default/victoriag/synth_data/self-talk/follow-up_persona_500samples_8turns_2completions_gpt3.5_gpt3.5_tulupref.jsonl --sanity_check --push_to_hub --temperature 1.0
- Downloads last month
- 4