[Update] Add QWQ32b model config (#1959)
Some checks are pending
lint / lint (push) Waiting to run

* feat qwq-32b

* fix

* feat phi_4

---------

Co-authored-by: Linchen Xiao <xxllcc1993@gmail.com>
This commit is contained in:
Myhs_phz 2025-03-24 14:51:39 +08:00 committed by GitHub
parent db96161a4e
commit 37307fa996
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194

View File

@ -0,0 +1,17 @@
from opencompass.models import TurboMindModelwithChatTemplate
from opencompass.utils.text_postprocessors import extract_non_reasoning_content
models = [
dict(
type=TurboMindModelwithChatTemplate,
abbr='QwQ-32B',
path='Qwen/QwQ-32B',
engine_config=dict(session_len=32768, max_batch_size=16, tp=2),
gen_config=dict(top_k=1, temperature=1e-6, top_p=0.9, max_new_tokens=8192),
max_seq_len=32768,
max_out_len=8192,
batch_size=16,
run_cfg=dict(num_gpus=2),
pred_postprocessor=dict(type=extract_non_reasoning_content)
)
]