README.md

metadata

language:
  - en
license: apache-2.0
task_categories:
  - text-generation
dataset_info:
  features:
    - name: text
      dtype: string
  splits:
    - name: train
      num_bytes: 20912557
      num_examples: 9846
    - name: test
      num_bytes: 1108538
      num_examples: 518
  download_size: 10221850
  dataset_size: 22021095
configs:
  - config_name: default
    data_files:
      - split: train
        path: data/train-*
      - split: test
        path: data/test-*

This dataset is timdettmers/openassistant-guanaco converted to what I believe to be the Llama 2 prompt format (based on this Reddit post). It is otherwise unchanged.

The format is like this:

<s>[INST] <<SYS>>
You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe.  Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.

If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.
<</SYS>>

{question} [/INST]
{response}

...where {question} is what the user asks first, and {response} is how the model is expected to respond. Further conversation turns are simply appended like this:

[INST]
{next_question}[/INST]
{next_response}

The license is the same as the original, Apache 2.0.