|
--- |
|
language: |
|
- ru |
|
size_categories: |
|
- 1K<n<10K |
|
task_categories: |
|
- question-answering |
|
- text-classification |
|
- text-generation |
|
pretty_name: R |
|
dataset_info: |
|
features: |
|
- name: topic |
|
dtype: string |
|
- name: user_question |
|
dtype: string |
|
- name: assistant_answer |
|
dtype: string |
|
- name: to_doctor |
|
dtype: string |
|
- name: __index_level_0__ |
|
dtype: int64 |
|
- name: prompt |
|
dtype: string |
|
splits: |
|
- name: train |
|
num_bytes: 7995673.941131692 |
|
num_examples: 3546 |
|
- name: test |
|
num_bytes: 890663.0588683075 |
|
num_examples: 395 |
|
download_size: 3764582 |
|
dataset_size: 8886337.0 |
|
configs: |
|
- config_name: default |
|
data_files: |
|
- split: train |
|
path: data/train-* |
|
- split: test |
|
path: data/test-* |
|
tags: |
|
- medical |
|
- biology |
|
- synthetic |
|
--- |
|
|
|
# Russian-language dataset of 3941 patient conversations with a medical bot in QA manner. |
|
* The **training sample** includes 3546 conversations; |
|
* The **test sample** includes 395 conversations; |
|
|
|
## Feature characteristics: |
|
* *topic* - medical topic |
|
* *user_question* - last user question |
|
* *assistant_answer* - ai answer according the context and topic |
|
* *to_doctor* - the specialty of the physician to whom the assistant referred the patient |
|
* *prompt* - ready prompt for fincetuning instruct phi model (adapted for using with unsloth https://github.com/unslothai/unsloth?tab=readme-ov-file) |
|
|
|
## Prompt format: |
|
<|user|>USER QUESTION<|end|>\n<|assistant|>ASSISTANT ANSWER<|end|> |
|
|
|
# Disclaimer |
|
The data provided is solely for research purposes. It may include inaccuracies, potentially harmful content, or biases, and we disclaim any responsibility for these issues. Users should assess the data's accuracy and appropriateness before utilizing it. The opinions and views represented in the data do not necessarily align with those of the author. |
