unsloth/studio/backend/models
Roland Tannous 9a818e7155 studio: add normalize_gguf_quantization_method helper + tests
Introduce a pure helper that coerces Union[str, List[str]] inputs to
a lowercase, deduplicated list, rejecting empty lists via ValueError.
The ExportGGUFRequest.quantization_method field type is widened to
Union[str, List[str]] to accept batch inputs without breaking legacy
single-format callers.

The helper is the single point of normalization for the GGUF export
API boundary; routes/export.py will call it in the next commit.

Hermetic pytest at studio/backend/tests/test_export_gguf_batching.py
covers string-to-list wrapping, list lowercasing, order-preserving
dedup, empty-list rejection, and the three Pydantic-integration paths
(default, string input, list input).
2026-04-14 22:31:20 +04:00
..
.gitkeep fix: restore models directory files deleted during restructure 2026-02-02 19:36:30 +00:00
__init__.py feat(studio): training history persistence and past runs viewer (#4501) 2026-03-25 00:58:55 -07:00
auth.py Studio: Expose openai and anthropic compatible external API end points (#4956) 2026-04-13 21:08:11 +04:00
data_recipe.py feat(studio): multi-file unstructured seed upload with better backend extraction (#4468) 2026-03-20 13:22:42 -07:00
datasets.py Final cleanup 2026-03-12 18:28:04 +00:00
export.py studio: add normalize_gguf_quantization_method helper + tests 2026-04-14 22:31:20 +04:00
inference.py Studio: Expose openai and anthropic compatible external API end points (#4956) 2026-04-13 21:08:11 +04:00
models.py feat: custom scan folders for GGUF model discovery (#4723) 2026-03-31 06:40:31 -07:00
responses.py Final cleanup 2026-03-12 18:28:04 +00:00
training.py fix(studio): correct default weight_decay and learning rate (#4695) 2026-03-31 13:50:25 +04:00
users.py fix: remove old comments (#4292) 2026-03-14 16:50:13 +04:00