ipex-llm/python/llm/src/ipex_llm/transformers/load_config.yaml
Guancheng Fu 74997a3ed1
Adding load_low_bit interface for ipex_llm_worker (#11000)
* initial implementation, need tests

* fix

* fix baichuan issue

* fix typo
2024-05-13 15:30:19 +08:00

16 lines
522 B
YAML

# TODO: move this to a different repo
repo_id:
# - 'THUDM/chatglm-6b'
# - 'THUDM/chatglm2-6b'
- 'meta-llama/Llama-2-7b-chat-hf'
# - 'baichuan-inc/Baichuan2-7B-Chat'
# - 'Qwen/Qwen-7B-Chat'
# - 'liuhaotian/llava-v1.5-7b' # requires a LLAVA_REPO_DIR env variables pointing to the llava dir; added only for gpu win related test_api now
local_model_hub: '/mnt/disk1/models'
low_bit:
- 'sym_int4' # default to use 'sym_int4' (i.e. symmetric int4)
- 'bf16'
device:
#- 'cpu'
- 'xpu'
load_low_bit_model: False