jiangzhs/OpenCompass
1
0
Fork 0
mirror of https://github.com/open-compass/opencompass.git synced 2025-05-30 16:03:24 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[Update] Add Long-Context configs for Gemma, OREAL, and Qwen2.5 models (#2048)

Browse Source 
* [Update] Update Gemma, Oreal, Qwen Config

* fix lint
This commit is contained in:
Mo Li 2025-05-08 19:06:56 +08:00 committed by GitHub
parent a685ed7daf
commit ff3275edf0
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
9 changed files with 172 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
opencompass/configs/models/gemma/vllm_gemma_3_12b_it.py Normal file
View File

@ -0,0 +1,16 @@
from opencompass.models import VLLMwithChatTemplate
models = [
dict(
type=VLLMwithChatTemplate,
abbr='gemma-3-12b-it-vllm',
path='google/gemma-3-12b-it',
model_kwargs=dict(tensor_parallel_size=4,
# for long context
rope_scaling={'factor': 8.0, 'rope_type': 'linear'}),
max_out_len=4096,
batch_size=1,
generation_kwargs=dict(temperature=0),
run_cfg=dict(num_gpus=4),
)
]

16
opencompass/configs/models/gemma/vllm_gemma_3_27b_it.py Normal file
View File

@ -0,0 +1,16 @@
from opencompass.models import VLLMwithChatTemplate
models = [
dict(
type=VLLMwithChatTemplate,
abbr='gemma-3-27b-it-vllm',
path='google/gemma-3-27b-it',
model_kwargs=dict(tensor_parallel_size=4,
# for long context
rope_scaling={'factor': 8.0, 'rope_type': 'linear'}),
max_out_len=4096,
batch_size=1,
generation_kwargs=dict(temperature=0),
run_cfg=dict(num_gpus=4),
)
]

17
opencompass/configs/models/gemma/vllm_gemma_3_4b_it.py Normal file
View File

@ -0,0 +1,17 @@
from opencompass.models import VLLMwithChatTemplate
models = [
dict(
type=VLLMwithChatTemplate,
abbr='gemma-3-4b-it-vllm',
path='google/gemma-3-4b-it',
model_kwargs=dict(tensor_parallel_size=2,
# for long context
rope_scaling={'factor': 8.0, 'rope_type': 'linear'}),
max_seq_len=140000,
max_out_len=4096,
batch_size=1,
generation_kwargs=dict(temperature=0),
run_cfg=dict(num_gpus=2),
)
]

19
opencompass/configs/models/hf_internlm/lmdeploy_internlm3_8b_instruct_128k.py Normal file
View File

@ -0,0 +1,19 @@
from opencompass.models import TurboMindModelwithChatTemplate
models = [
dict(
type=TurboMindModelwithChatTemplate,
abbr='internlm3-8b-instruct-turbomind',
path='internlm/internlm3-8b-instruct',
engine_config=dict(session_len=142000, max_batch_size=1, tp=2,
# for long context
rope_scaling_factor=6.0),
gen_config=dict(
top_k=1, temperature=1e-6, top_p=0.9, max_new_tokens=8192
),
max_seq_len=142000,
max_out_len=8192,
batch_size=1,
run_cfg=dict(num_gpus=2),
)
]

20
opencompass/configs/models/hf_internlm/lmdeploy_oreal_32b.py Normal file
View File

@ -0,0 +1,20 @@
from opencompass.models import TurboMindModelwithChatTemplate
from opencompass.utils.text_postprocessors import extract_non_reasoning_content
models = [
dict(
type=TurboMindModelwithChatTemplate,
abbr='OREAL-32B',
path='internlm/OREAL-32B',
engine_config=dict(session_len=32768, max_batch_size=16, tp=4),
gen_config=dict(top_k=1,
temperature=1e-6,
top_p=0.9,
max_new_tokens=32768),
max_seq_len=32768,
max_out_len=32768,
batch_size=16,
run_cfg=dict(num_gpus=4),
pred_postprocessor=dict(type=extract_non_reasoning_content)
)
]

21
opencompass/configs/models/qwen2_5/vllm_qwen2_5_14b_instruct_128k.py Normal file
View File

@ -0,0 +1,21 @@
from opencompass.models import VLLMwithChatTemplate
models = [
dict(
type=VLLMwithChatTemplate,
abbr='qwen2.5-14b-instruct-vllm',
path='Qwen/Qwen2.5-14B-Instruct',
model_kwargs=dict(
tensor_parallel_size=4,
rope_scaling={
'factor': 4.0,
'original_max_position_embeddings': 32768,
'rope_type': 'yarn'
},
),
max_out_len=4096,
batch_size=1,
generation_kwargs=dict(temperature=0),
run_cfg=dict(num_gpus=4),
)
]

21
opencompass/configs/models/qwen2_5/vllm_qwen2_5_32b_instruct_128k.py Normal file
View File

@ -0,0 +1,21 @@
from opencompass.models import VLLMwithChatTemplate
models = [
dict(
type=VLLMwithChatTemplate,
abbr='qwen2.5-32b-instruct-vllm',
path='Qwen/Qwen2.5-32B-Instruct',
model_kwargs=dict(
tensor_parallel_size=8,
rope_scaling={
'factor': 4.0,
'original_max_position_embeddings': 32768,
'rope_type': 'yarn'
},
),
max_out_len=4096,
batch_size=1,
generation_kwargs=dict(temperature=0),
run_cfg=dict(num_gpus=8),
)
]

21
opencompass/configs/models/qwen2_5/vllm_qwen2_5_72b_instruct_128k.py Normal file
View File

@ -0,0 +1,21 @@
from opencompass.models import VLLMwithChatTemplate
models = [
dict(
type=VLLMwithChatTemplate,
abbr='qwen2_5-72b-instruct-vllm',
path='Qwen/Qwen2.5-72B-Instruct',
model_kwargs=dict(
tensor_parallel_size=8,
rope_scaling={
'factor': 4.0,
'original_max_position_embeddings': 32768,
'rope_type': 'yarn'
},
),
max_out_len=4096,
batch_size=1,
generation_kwargs=dict(temperature=0),
run_cfg=dict(num_gpus=8),
)
]

21
opencompass/configs/models/qwen2_5/vllm_qwen2_5_7b_instruct_128k.py Normal file
View File

@ -0,0 +1,21 @@
from opencompass.models import VLLMwithChatTemplate
models = [
dict(
type=VLLMwithChatTemplate,
abbr='qwen2.5-7b-instruct-vllm',
path='Qwen/Qwen2.5-7B-Instruct',
model_kwargs=dict(
tensor_parallel_size=4,
rope_scaling={
'factor': 4.0,
'original_max_position_embeddings': 32768,
'rope_type': 'yarn'
},
),
max_out_len=4096,
batch_size=1,
generation_kwargs=dict(temperature=0),
run_cfg=dict(num_gpus=4),
)
]