FangYin Cheng d8a4b776d5 feat: Support 8-bit quantization and 4-bit quantization for multi-gpu inference

2023-08-02 19:29:59 +08:00

..

cache

style:format code

2023-06-27 22:20:21 +08:00

llm

ci: make ci happy lint the code, delete unused imports

2023-05-24 18:43:04 +08:00

llm_out

refactor: rename the data privacy module

2023-07-28 14:45:27 +08:00

proxy

fix: simply the code and optimization

2023-07-31 19:19:39 +08:00

__init__.py

update

2023-04-28 22:48:39 +08:00

adapter.py

feat: Support 8-bit quantization and 4-bit quantization for multi-gpu inference

2023-08-02 19:29:59 +08:00

base.py

ci: make ci happy lint the code, delete unused imports

2023-05-24 18:43:04 +08:00

compression.py

ci: make ci happy lint the code, delete unused imports

2023-05-24 18:43:04 +08:00

conversation.py

feat: Support baichuan-7B model

2023-07-25 22:08:07 +08:00

inference.py

feat: Support llama-2 model

2023-07-20 21:44:40 +08:00

llm_utils.py

feat: Support llama-2 model

2023-07-20 21:44:40 +08:00

loader.py

feat: Support 8-bit quantization and 4-bit quantization for multi-gpu inference

2023-08-02 19:29:59 +08:00