MMIRAGE/configs/config_mock_openai_batch.yaml at 71f9d6f355b4fc21d2a6b251432ad2bc2f83860f · EPFLiGHT/MMIRAGE · GitHub

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
processors:
  - type: llm
    server_args:
      model_path: Qwen/Qwen3-4B-Instruct-2507
      tp_size: 1
      disable_custom_all_reduce: true
    default_sampling_params:
      temperature: 0.1
      top_p: 0.9
      max_new_tokens: 1024
      custom_params:
        chat_template_kwargs:
          enable_thinking: false
    batch_provider:
      enabled: true
      provider: openai
      model: gpt-4o-mini
      max_chunk_bytes: 52428800
      metadata_output_path: tests/output/batch_metadata.jsonl
      credentials:
        api_key:

loading_params:
  datasets:
    - path: tests/mock_data/data.jsonl
      type: JSONL
      output_dir: tests/output/data_openai_batch

  num_shards: 1
  shard_id: 0
  batch_size: 64

processing_params:
  inputs:
    - name: text
      key: text

  outputs:
    - name: formatted_answer
      type: llm
      output_type: JSON
      output_schema:
        - question
        - answer
      prompt: |
        Generate one question and its corresponding answer using the following text:
        ```
        {{ text }}
        ```

  remove_columns: true
  output_schema:
    conversations:
      - role: "user"
        content: "{{ formatted_answer.question }}"
      - role: "assistant"
        content: "{{ formatted_answer.answer }}"