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

fixed typo for mistral model configs

Browse Source
This commit is contained in:
linjunyao 2025-01-07 08:49:57 +00:00
parent f871e80887
commit 7327e3a467
7 changed files with 58 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
configs/models/mistral/lmdeploy_mixtral_large_instruct_2407.py → configs/models/mistral/lmdeploy_mistral_large_instruct_2407.py
View File

@ -3,7 +3,7 @@ from opencompass.models import TurboMindModelwithChatTemplate
models = [
dict(
type=TurboMindModelwithChatTemplate,
abbr='mixtral-large-instruct-2407-turbomind',
abbr='mistral-large-instruct-2407-turbomind',
path='mistralai/Mistral-Large-Instruct-2407',
engine_config=dict(
session_len=32768,
@ -11,9 +11,7 @@ models = [
tp=4,
cache_max_entry_count=0.7,
),
gen_config=dict(
top_k=1, temperature=1e-6, top_p=0.9, max_new_tokens=4096
),
gen_config=dict(top_k=1, temperature=1e-6, top_p=0.9, max_new_tokens=4096),
max_seq_len=32768,
max_out_len=4096,
batch_size=8,

20
configs/models/mistral/lmdeploy_mistral_large_instruct_2411.py Normal file
View File

@ -0,0 +1,20 @@
from opencompass.models import TurboMindModelwithChatTemplate
models = [
dict(
type=TurboMindModelwithChatTemplate,
abbr='mistral-large-instruct-2411-turbomind',
path='mistralai/Mistral-Large-Instruct-2411',
engine_config=dict(
session_len=32768,
max_batch_size=16,
tp=4,
cache_max_entry_count=0.7,
),
gen_config=dict(top_k=1, temperature=1e-6, top_p=0.9, max_new_tokens=4096),
max_seq_len=32768,
max_out_len=4096,
batch_size=8,
run_cfg=dict(num_gpus=4),
)
]

15
configs/models/mistral/lmdeploy_mistral_nemo_instruct_2407.py Normal file
View File

@ -0,0 +1,15 @@
from opencompass.models import TurboMindModelwithChatTemplate
models = [
dict(
type=TurboMindModelwithChatTemplate,
abbr='mistral-nemo-instruct-2407-turbomind',
path='mistralai/Mistral-Nemo-Instruct-2407',
engine_config=dict(session_len=32768, max_batch_size=16, tp=1),
gen_config=dict(top_k=1, temperature=1e-6, top_p=0.9, max_new_tokens=4096),
max_seq_len=32768,
max_out_len=4096,
batch_size=16,
run_cfg=dict(num_gpus=1),
)
]

15
configs/models/mistral/lmdeploy_mistral_small_instruct_2409.py Normal file
View File

@ -0,0 +1,15 @@
from opencompass.models import TurboMindModelwithChatTemplate
models = [
dict(
type=TurboMindModelwithChatTemplate,
abbr='mistral-small-instruct-2409-turbomind',
path='mistralai/Mistral-Small-Instruct-2409',
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=4096),
max_seq_len=32768,
max_out_len=4096,
batch_size=16,
run_cfg=dict(num_gpus=2),
)
]

6
opencompass/configs/models/mistral/lmdeploy_mixtral_large_instruct_2407.py → opencompass/configs/models/mistral/lmdeploy_mistral_large_instruct_2407.py
View File

@ -3,7 +3,7 @@ from opencompass.models import TurboMindModelwithChatTemplate
models = [
dict(
type=TurboMindModelwithChatTemplate,
abbr='mixtral-large-instruct-2407-turbomind',
abbr='mistral-large-instruct-2407-turbomind',
path='mistralai/Mistral-Large-Instruct-2407',
engine_config=dict(
session_len=32768,
@ -11,9 +11,7 @@ models = [
tp=4,
cache_max_entry_count=0.7,
),
gen_config=dict(
top_k=1, temperature=1e-6, top_p=0.9, max_new_tokens=4096
),
gen_config=dict(top_k=1, temperature=1e-6, top_p=0.9, max_new_tokens=4096),
max_seq_len=32768,
max_out_len=4096,
batch_size=8,

6
opencompass/configs/models/mistral/lmdeploy_mistral_large_instruct_2411.py
View File

@ -3,7 +3,7 @@ from opencompass.models import TurboMindModelwithChatTemplate
models = [
dict(
type=TurboMindModelwithChatTemplate,
abbr='mixtral-large-instruct-2411-turbomind',
abbr='mistral-large-instruct-2411-turbomind',
path='mistralai/Mistral-Large-Instruct-2411',
engine_config=dict(
session_len=32768,
@ -11,9 +11,7 @@ models = [
tp=4,
cache_max_entry_count=0.7,
),
gen_config=dict(
top_k=1, temperature=1e-6, top_p=0.9, max_new_tokens=4096
),
gen_config=dict(top_k=1, temperature=1e-6, top_p=0.9, max_new_tokens=4096),
max_seq_len=32768,
max_out_len=4096,
batch_size=8,

4
opencompass/configs/models/mistral/lmdeploy_mistral_small_instruct_2409.py
View File

@ -3,8 +3,8 @@ from opencompass.models import TurboMindModelwithChatTemplate
models = [
dict(
type=TurboMindModelwithChatTemplate,
abbr="mistral-small-instruct-2409-turbomind",
path="mistralai/Mistral-Small-Instruct-2409",
abbr='mistral-small-instruct-2409-turbomind',
path='mistralai/Mistral-Small-Instruct-2409',
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=4096),
max_seq_len=32768,