1d7d167b29
Replace ad-hoc JSON parsing with a strict Pydantic model (TrainingExample with typed OutputPair). All data loading goes through load_examples() which fails loudly on invalid data. - Convert v3_structured.jsonl from "searches" to "output" format - Rewrite all consumer scripts (prepare, validate, score, analyze) to load through the Pydantic schema - Prepared train/val files are ephemeral build artifacts - Restore LFM2 and GEPA experiments under experiments/ - Add pydantic>=2.0 to dependencies
24 lines
409 B
TOML
24 lines
409 B
TOML
[project]
|
|
name = "qmd-finetune"
|
|
version = "0.1.0"
|
|
description = "QMD query expansion fine-tuning tools"
|
|
requires-python = ">=3.10"
|
|
dependencies = [
|
|
"torch",
|
|
"trl>=0.12.0",
|
|
"peft>=0.7.0",
|
|
"transformers>=4.45.0",
|
|
"accelerate>=0.24.0",
|
|
"huggingface_hub>=0.20.0",
|
|
"trackio",
|
|
"datasets",
|
|
"pyyaml",
|
|
"gguf",
|
|
"sentencepiece",
|
|
"nvidia-ml-py",
|
|
"pydantic>=2.0",
|
|
]
|
|
|
|
[dependency-groups]
|
|
dev = []
|