OpenCompass/configs/eval_needleinahaystack_turbomind.py
Mo Li acae560911
Added support for multi-needle testing in needle-in-a-haystack test (#802)
* Add NeedleInAHaystack Test

* Apply pre-commit formatting

* Update configs/eval_hf_internlm_chat_20b_cdme.py

Co-authored-by: Songyang Zhang <tonysy@users.noreply.github.com>

* add needle in haystack test

* update needle in haystack test

* update plot function in tools_needleinahaystack.py

* optimizing needleinahaystack dataset generation strategy

* modify minor formatting issues

* add English version support

* change NeedleInAHaystackDataset to dynamic loading

* change NeedleInAHaystackDataset to dynamic loading

* fix needleinahaystack test eval bug

* fix needleinahaystack config bug

* Added support for multi-needle testing in needle-in-a-haystack test

* Optimize the code for plotting in the needle-in-a-haystack test.

* Correct the typo in the dataset parameters.

* update needleinahaystack test docs

---------

Co-authored-by: Songyang Zhang <tonysy@users.noreply.github.com>
2024-01-17 13:47:34 +08:00

29 lines
769 B
Python

from opencompass.models.turbomind import TurboMindModel
from mmengine.config import read_base
with read_base():
from .datasets.cdme.cdme200k import cdme_datasets
datasets = [*cdme_datasets]
internlm_meta_template = dict(round=[
dict(role='HUMAN', begin='<|User|>:', end='\n'),
dict(role='BOT', begin='<|Bot|>:', end='<eoa>\n', generate=True),
],
eos_token_id=103028)
models = [
# config for internlm-chat-20b
dict(
type=TurboMindModel,
abbr='internlm-chat-20b-turbomind',
path='./turbomind',
max_out_len=100,
max_seq_len=201000,
batch_size=8,
concurrency=8,
meta_template=internlm_meta_template,
run_cfg=dict(num_gpus=1, num_procs=1),
)
]