Alpamys 20c2f4e515 fix: use AutoModel for audio, is_relative_to path check, early librosa import ... - Use AutoModel instead of AutoModelForCausalLM for audio-language models (Qwen2-Audio, Whisper don't work with causal LM auto class) - Use Path.is_relative_to() for path traversal check (symlink-safe, Python 3.9+) - Fail fast with helpful error if librosa not installed before dataset processing		2026-03-26 13:59:46 +05:00
..
__init__.py	Initial project setup: CLI skeleton + config + trainer + data pipeline	2026-02-20 16:14:56 +05:00
dpo.py	v0.15.0: performance + long-context fine-tuning	2026-03-26 11:26:48 +05:00
embedding.py	v0.16.0: embedding models, ONNX/TensorRT export, speculative decoding	2026-03-26 12:41:39 +05:00
grpo.py	v0.15.0: performance + long-context fine-tuning	2026-03-26 11:26:48 +05:00
ipo.py	v0.15.0: performance + long-context fine-tuning	2026-03-26 11:26:48 +05:00
kto.py	v0.15.0: performance + long-context fine-tuning	2026-03-26 11:26:48 +05:00
orpo.py	v0.15.0: performance + long-context fine-tuning	2026-03-26 11:26:48 +05:00
ppo.py	v0.15.0: performance + long-context fine-tuning	2026-03-26 11:26:48 +05:00
pretrain.py	v0.15.0: performance + long-context fine-tuning	2026-03-26 11:26:48 +05:00
reward_model.py	v0.15.0: performance + long-context fine-tuning	2026-03-26 11:26:48 +05:00
rewards.py	v0.10.10: Security hardening — Web UI auth, CORS, SSRF, path traversal protection	2026-03-25 12:14:10 +05:00
sft.py	fix: use AutoModel for audio, is_relative_to path check, early librosa import	2026-03-26 13:59:46 +05:00
simpo.py	v0.15.0: performance + long-context fine-tuning	2026-03-26 11:26:48 +05:00