Files
llm-arch-research/llm/tests/core
Sergey Penkovsky db0ab511d1 feat(gpt2): add Gpt2Decoder module, refactor model and add tests
- Implemented core/gpt2_decoder.py: transformer decoder block with kv cache in GPT2 style
- Refactored models/gpt/gpt2.py to use new Gpt2Decoder, improved documentation
- Added tests/core/test_gpt2_decoder.py for main features and cache
- Temporarily skipped HF proxy integration test for compatibility
2025-10-31 15:35:54 +03:00
..