mirror of
https://github.com/open-compass/opencompass.git
synced 2025-05-30 16:03:24 +08:00
b52ba65c26
* integrate lmdeploy's pipeline api * fix linting * update user guide * rename * update * update * update * rollback class name * update * remove unused code * update * update * fix ci check * compatibility * remove concurrency * Update configs/models/hf_internlm/lmdeploy_internlm2_chat_7b.py * Update docs/zh_cn/advanced_guides/evaluation_lmdeploy.md * [Bug] fix lint --------- Co-authored-by: Songyang Zhang <tonysy@users.noreply.github.com> Co-authored-by: tonysy <sy.zhangbuaa@gmail.com>
25 lines
871 B
Python
25 lines
871 B
Python
from opencompass.models import TurboMindModelwithChatTemplate
|
|
|
|
|
|
models = [
|
|
dict(
|
|
type=TurboMindModelwithChatTemplate,
|
|
abbr=f'internlm2-chat-7b-lmdeploy',
|
|
path='internlm/internlm2-chat-7b',
|
|
# inference backend of LMDeploy. It can be either 'turbomind' or 'pytorch'.
|
|
# If the model is not supported by 'turbomind', it will fallback to
|
|
# 'pytorch'
|
|
backend='turbomind',
|
|
# For the detailed engine config and generation config, please refer to
|
|
# https://github.com/InternLM/lmdeploy/blob/main/lmdeploy/messages.py
|
|
engine_config=dict(tp=1),
|
|
gen_config=dict(do_sample=False),
|
|
max_seq_len=8192,
|
|
max_out_len=4096,
|
|
# the max number of prompts that LMDeploy receives
|
|
# in `generate` function
|
|
batch_size=5000,
|
|
run_cfg=dict(num_gpus=1),
|
|
)
|
|
]
|