mirror of
https://github.com/open-compass/opencompass.git
synced 2025-05-30 16:03:24 +08:00
fixed typo for mistral model configs
This commit is contained in:
parent
f871e80887
commit
7327e3a467
@ -3,7 +3,7 @@ from opencompass.models import TurboMindModelwithChatTemplate
|
|||||||
models = [
|
models = [
|
||||||
dict(
|
dict(
|
||||||
type=TurboMindModelwithChatTemplate,
|
type=TurboMindModelwithChatTemplate,
|
||||||
abbr='mixtral-large-instruct-2407-turbomind',
|
abbr='mistral-large-instruct-2407-turbomind',
|
||||||
path='mistralai/Mistral-Large-Instruct-2407',
|
path='mistralai/Mistral-Large-Instruct-2407',
|
||||||
engine_config=dict(
|
engine_config=dict(
|
||||||
session_len=32768,
|
session_len=32768,
|
||||||
@ -11,9 +11,7 @@ models = [
|
|||||||
tp=4,
|
tp=4,
|
||||||
cache_max_entry_count=0.7,
|
cache_max_entry_count=0.7,
|
||||||
),
|
),
|
||||||
gen_config=dict(
|
gen_config=dict(top_k=1, temperature=1e-6, top_p=0.9, max_new_tokens=4096),
|
||||||
top_k=1, temperature=1e-6, top_p=0.9, max_new_tokens=4096
|
|
||||||
),
|
|
||||||
max_seq_len=32768,
|
max_seq_len=32768,
|
||||||
max_out_len=4096,
|
max_out_len=4096,
|
||||||
batch_size=8,
|
batch_size=8,
|
@ -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),
|
||||||
|
)
|
||||||
|
]
|
@ -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),
|
||||||
|
)
|
||||||
|
]
|
@ -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),
|
||||||
|
)
|
||||||
|
]
|
@ -3,7 +3,7 @@ from opencompass.models import TurboMindModelwithChatTemplate
|
|||||||
models = [
|
models = [
|
||||||
dict(
|
dict(
|
||||||
type=TurboMindModelwithChatTemplate,
|
type=TurboMindModelwithChatTemplate,
|
||||||
abbr='mixtral-large-instruct-2407-turbomind',
|
abbr='mistral-large-instruct-2407-turbomind',
|
||||||
path='mistralai/Mistral-Large-Instruct-2407',
|
path='mistralai/Mistral-Large-Instruct-2407',
|
||||||
engine_config=dict(
|
engine_config=dict(
|
||||||
session_len=32768,
|
session_len=32768,
|
||||||
@ -11,9 +11,7 @@ models = [
|
|||||||
tp=4,
|
tp=4,
|
||||||
cache_max_entry_count=0.7,
|
cache_max_entry_count=0.7,
|
||||||
),
|
),
|
||||||
gen_config=dict(
|
gen_config=dict(top_k=1, temperature=1e-6, top_p=0.9, max_new_tokens=4096),
|
||||||
top_k=1, temperature=1e-6, top_p=0.9, max_new_tokens=4096
|
|
||||||
),
|
|
||||||
max_seq_len=32768,
|
max_seq_len=32768,
|
||||||
max_out_len=4096,
|
max_out_len=4096,
|
||||||
batch_size=8,
|
batch_size=8,
|
@ -3,7 +3,7 @@ from opencompass.models import TurboMindModelwithChatTemplate
|
|||||||
models = [
|
models = [
|
||||||
dict(
|
dict(
|
||||||
type=TurboMindModelwithChatTemplate,
|
type=TurboMindModelwithChatTemplate,
|
||||||
abbr='mixtral-large-instruct-2411-turbomind',
|
abbr='mistral-large-instruct-2411-turbomind',
|
||||||
path='mistralai/Mistral-Large-Instruct-2411',
|
path='mistralai/Mistral-Large-Instruct-2411',
|
||||||
engine_config=dict(
|
engine_config=dict(
|
||||||
session_len=32768,
|
session_len=32768,
|
||||||
@ -11,9 +11,7 @@ models = [
|
|||||||
tp=4,
|
tp=4,
|
||||||
cache_max_entry_count=0.7,
|
cache_max_entry_count=0.7,
|
||||||
),
|
),
|
||||||
gen_config=dict(
|
gen_config=dict(top_k=1, temperature=1e-6, top_p=0.9, max_new_tokens=4096),
|
||||||
top_k=1, temperature=1e-6, top_p=0.9, max_new_tokens=4096
|
|
||||||
),
|
|
||||||
max_seq_len=32768,
|
max_seq_len=32768,
|
||||||
max_out_len=4096,
|
max_out_len=4096,
|
||||||
batch_size=8,
|
batch_size=8,
|
||||||
|
@ -3,8 +3,8 @@ from opencompass.models import TurboMindModelwithChatTemplate
|
|||||||
models = [
|
models = [
|
||||||
dict(
|
dict(
|
||||||
type=TurboMindModelwithChatTemplate,
|
type=TurboMindModelwithChatTemplate,
|
||||||
abbr="mistral-small-instruct-2409-turbomind",
|
abbr='mistral-small-instruct-2409-turbomind',
|
||||||
path="mistralai/Mistral-Small-Instruct-2409",
|
path='mistralai/Mistral-Small-Instruct-2409',
|
||||||
engine_config=dict(session_len=32768, max_batch_size=16, tp=2),
|
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),
|
gen_config=dict(top_k=1, temperature=1e-6, top_p=0.9, max_new_tokens=4096),
|
||||||
max_seq_len=32768,
|
max_seq_len=32768,
|
||||||
|
Loading…
Reference in New Issue
Block a user