File size: 3,668 Bytes
60830a5 31dff87 c5bd4de 5ab25e7 be27af2 c5bd4de 5ab25e7 9683de3 c5bd4de 9683de3 c5bd4de 9683de3 c5bd4de |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 |
---
language:
- zh
- ne
- uk
- ja
- zu
- ku
- ig
- mg
- fi
- si
- id
- sw
- ar
- sv
- ru
- yo
- en
- ht
- kn
- ta
- te
- sq
- mr
- am
- wo
- it
- tr
- ha
- pl
- el
- lt
- ms
- jv
- sn
- ml
- ps
- ky
- es
- ga
- gu
- ko
- vi
- sd
- fa
- nl
- hu
- so
- pa
- bn
- pt
- da
- hi
- eu
- de
- ur
- su
- xh
- fr
license: cc-by-nc-sa-4.0
task_categories:
- text-generation
dataset_info:
- config_name: seed_data
splits:
- name: train
num_examples: 13686
- config_name: seed_evol_data
splits:
- name: train
num_examples: 102423
- config_name: full_data
splits:
- name: train
num_examples: 173672
configs:
- config_name: seed_data
data_files: seed_data.parquet
- config_name: seed_evol_data
data_files: seed_evol_data.parquet
- config_name: full_data
data_files: full_data.parquet
---
# M2Lingual
A _**M**ulti-turn_ _**M**ultilingual_ dataset for Instruction Fine-tuning LLMs - [Paper](https://huggingface.co/papers/2406.16783)
Code: https://github.com/ServiceNow/M2Lingual
## Dataset Summary
The M2Lingual dataset is a comprehensive multi-turn multilingual resource designed to facilitate research and development in conversational AI. It encompasses a wide range of conversation scenarios across multiple languages, making it an invaluable asset for training, evaluating, and benchmarking conversational models. The dataset includes diverse tasks such as question answering, task completion, summarization and more. Each entry is annotated with information about the conversation's evolution, including task Evol type, multi-turn Evol type, prompts, and the number of turns. The M2Lingual dataset aims to bridge the gap in multi-turn multilingual conversational data, providing a robust foundation for building more inclusive and effective AI systems that can understand and engage in human-like conversations across languages.
Here is a walkthrough example conversation, the first step involves selecting seeds, the second step evolves the seed sample, and the third step sets a multi-turn evolution which leads to a diverse multi-turn multilingual dataset:
## Dataset Instances
Here is an example conversation:
```
{
"id": 8605,
"conversation": [
{
"role": "user",
"content": "Formulate an answer to this elaborate question: Identify the base location of the regional airline for which Jim French served as the former chairman and CEO, and explain the significance of this location in the context of the airline's regional operations."
},
{
"role": "assistant",
"content": "Jim French served as the former chairman and CEO of Flybe, a British regional airline. The base location of Flybe was Exeter International Airport in Devon, England.
The significance of Exeter International Airport as the base location for Flybe lies in its strategic positioning within the United Kingdom. Exeter is situated in the southwest region of England, which allowed Flybe to efficiently connect various regional destinations across the UK and Europe. This location provided a central hub for operations, facilitating shorter flight routes and quick turnaround times, which are essential for regional airlines aiming to offer frequent and reliable services. Additionally, having a base in Exeter helped Flybe tap into a market with fewer competing airlines, allowing it to establish a strong regional presence and foster economic growth within the southwest of England by improving connectivity and accessibility."
}, |