Matthew Farrellee a3e249807b chore: remove vision model URL workarounds and simplify client creation (#2775) ... The vision models are now available at the standard URL, so the workaround code has been removed. This also simplifies the codebase by eliminating the need for per-model client caching. - Remove special URL handling for meta/llama-3.2-11b/90b-vision-instruct models - Convert _get_client method to _client property for cleaner API - Remove unnecessary lru_cache decorator and functools import - Simplify client creation logic to use single base URL for all models		2025-07-16 07:10:04 -07:00
..
__init__.py	feat: Add nemo customizer (#1448)	2025-03-25 11:01:10 -07:00
conftest.py	chore: re-enable isort enforcement (#1802)	2025-03-26 15:22:17 -07:00
test_datastore.py	feat: Add NVIDIA NeMo datastore (#1852)	2025-04-28 09:41:59 -07:00
test_eval.py	feat: Add NVIDIA Eval integration (#1890)	2025-04-24 17:12:42 -07:00
test_parameters.py	fix: Pass model parameter as config name to NeMo Customizer (#2218)	2025-05-20 09:51:39 -07:00
test_safety.py	chore: remove nested imports (#2515)	2025-06-26 08:01:05 +05:30
test_supervised_fine_tuning.py	chore: remove vision model URL workarounds and simplify client creation (#2775)	2025-07-16 07:10:04 -07:00