Files
llm/plugins/1c/training/manifests/dataset.yaml
T

35 lines
1.3 KiB
YAML

id: 1c-instruction-v1
name: 1C Instruction Dataset v1
status: draft
format: chat-jsonl
example_path: plugins/1c/training/examples/instruction.examples.jsonl
generated_path: plugins/1c/training/raw/generated.instruction.jsonl
prepared_path: plugins/1c/training/prepared/train.chat.jsonl
validation:
script: scripts/validate_1c_training_data.py
generation:
script: scripts/generate_1c_training_data.py
sources:
- plugins/1c/metadata/examples/metadata-v2.example.json
- plugins/1c/metadata/examples/bsl-modules.example.json
- reports/1c-sql/upo_test/write-matrix-verified-registry-configsave-91ce.json
- reports/1c-sql/upo_test/write-matrix-verified-registry-configsave-fa44.json
- reports/1c-sql/upo_test/write-learning-plan-configsave-91ce.json
- reports/1c-sql/upo_test/write-learning-plan-configsave-fa44.json
write_artifacts:
verified_registry_limit_per_file: 25
learning_plan_limit_per_file: 12
privacy:
allow_client_data: false
require_secret_scan: true
require_expert_review: true
tasks:
- bsl-code
- metadata-safety
- metadata-write-verified
- metadata-write-learning-plan
- 1c-query
- explanation
notes: "Use curated, reviewed examples for quality training. Generated synthetic records are allowed for pipeline checks and guardrail pretraining, but still require review before production use."