hiyouga 3c330869ef improve quantization ...

Former-commit-id: 4dde60017ad8208dfea0b2bb61df6a14a35d03e0

2023-12-20 18:27:16 +08:00

..

__init__.py

fix #1558

2023-11-19 14:15:47 +08:00

adapter.py

refactor adapter hparam

2023-12-15 20:53:11 +08:00

loader.py

fix #1900

2023-12-19 17:21:46 +08:00

parser.py

support autogptq in llama board #246

2023-12-16 16:31:30 +08:00

patcher.py

improve quantization

2023-12-20 18:27:16 +08:00

utils.py

add max_memory for gptq #1923

2023-12-20 18:15:17 +08:00