Conversation

Conversation format for supervised fine-tuning.

sharegpt

UPDATE: ShareGPT is being deprecated in the next release. Please see chat_template section below.

conversations where from is human/gpt. (optional: first row with role system to override default system prompt)

data.jsonl

{"conversations": [{"from": "...", "value": "..."}]}

Note: type: sharegpt opens special configs: - conversation: enables conversions to many Conversation types. Refer to the ‘name’ here for options. - roles: allows you to specify the roles for input and output. This is useful for datasets with custom roles such as tool etc to support masking. - field_human: specify the key to use instead of human in the conversation. - field_model: specify the key to use instead of gpt in the conversation.

datasets:
    path: ...
    type: sharegpt

    conversation: # Options (see Conversation 'name'): https://github.com/lm-sys/FastChat/blob/main/fastchat/conversation.py
    field_human: # Optional[str]. Human key to use for conversation.
    field_model: # Optional[str]. Assistant key to use for conversation.
    # Add additional keys from your dataset as input or output roles
    roles:
      input: # Optional[List[str]]. These will be masked based on train_on_input
      output: # Optional[List[str]].

pygmalion

data.jsonl

{"conversations": [{"role": "...", "value": "..."}]}

sharegpt.load_role

conversations where role is used instead of from

data.jsonl

{"conversations": [{"role": "...", "value": "..."}]}

sharegpt.load_guanaco

conversations where from is prompter assistant instead of default sharegpt

data.jsonl

{"conversations": [{"from": "...", "value": "..."}]}

sharegpt.load_ultrachat

conversations where the turns field is ‘messages’, human is ‘user’ and gpt is ‘assistant’.

data.jsonl

{"messages": [{"user": "...", "assistant": "..."}]}

sharegpt_jokes

creates a chat where bot is asked to tell a joke, then explain why the joke is funny

data.jsonl

{"conversations": [{"title": "...", "text": "...", "explanation": "..."}]}

chat_template

Chat Template strategy uses a jinja2 template that converts a list of messages into a prompt. Support using tokenizer’s template, a supported template, or custom jinja2.

data.jsonl

{"conversations": [{"role": "...", "content": "..."}]}

See config.qmd for full configs and supported templates.

Migrating from sharegpt

Most configs can be adapted as follows:

# old
chat_template: chatml
datasets:
  - path: ...
    type: sharegpt
    conversation: chatml

# new (if using tokenizer's chat_template)
datasets:
  - path: ...
    type: chat_template

    field_messages: conversations
    message_field_role: from
    message_field_content: value

# new (if setting a new chat_template like chatml, gemma, etc)
chat_template: chatml
datasets:
  - path: ...
    type: chat_template

    field_messages: conversations
    message_field_role: from
    message_field_content: value

We recommend checking the below examples for other usecases.

Examples

Using the default chat template in the tokenizer_config.json on OpenAI messages format, training on only last message.

datasets:
  - path: ...
    type: chat_template

Using the gemma chat template to override the tokenizer_config.json’s chat template on OpenAI messages format, training on all assistant messages.

chat_template: gemma # this overwrites the tokenizer's chat_template
datasets:
  - path: ...
    type: chat_template
    roles_to_train: ["assistant"]

Using the tokenizer_config.json’s chat template or chatml as fallback if the former’s chat template does not exist, on OpenAI messages format, training on all assistant messages.

chat_template: tokenizer_default_fallback_chatml # this overwrites the tokenizer's chat_template
datasets:
  - path: ...
    type: chat_template
    roles_to_train: ["assistant"]

Using a custom jinja template on OpenAI messages format, training on all assistant messages.

# chat_template: jinja # `jinja` will be implied if the `chat_template_jinja` is set and this field is empty
chat_template_jinja: "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'system') %}{{'<|system|>' + '\n' + message['content'] + '<|end|>' + '\n'}}{% elif (message['role'] == 'user') %}{{'<|user|>' + '\n' + message['content'] + '<|end|>' + '\n' + '<|assistant|>' + '\n'}}{% elif message['role'] == 'assistant' %}{{message['content'] + '<|end|>' + '\n'}}{% endif %}{% endfor %}"

datasets:
  - path: ...
    type: chat_template
    roles_to_train: ["assistant"]

(Advanced) Using fine-grained control over tokens and turns to train in a conversation

For a data sample that looks like:

data.jsonl

{
  "conversations": [
    {"from": "system", "value": "You are an AI assistant.", "train": false},
    {"from": "human", "value": "Hello", "train": false},
    {"from": "assistant", "value": "Hello", "train": true},
    {"from": "human", "value": "How are you?", "train": true},
    {
      "from": "assistant",
      "value": "I'm doing very well, thank you!",
      "train_detail": [
        {"begin_offset": 0, "end_offset": 8, "train": false},
        {"begin_offset": 9, "end_offset": 18, "train": true},
        {"begin_offset": 19, "end_offset": 30, "train": false},
      ],
    },
    {
        "from": "human",
        "value": "I'm doing very well, thank you!",
        "train": true,
    },
    {"from": "assistant", "value": "Hi there!", "train": true}
  ]
}

The configuration would look like:

datasets:
  - path: ...
    type: chat_template
    chat_template: tokenizer_default
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    roles_to_train: []
    train_on_eos: turn
    message_field_training: train
    message_field_training_detail: train_detail

Tip: It is not necessary to use both message_field_training and message_field_training_detail at a time.