mirror of
https://github.com/open-compass/opencompass.git
synced 2025-05-30 16:03:24 +08:00
8e55c9c6ee
* stash files * compassbench subjective evaluation added * evaluation update * fix lint * update docs * Update lint * changes saved * changes saved * CompassBench subjective summarizer added (#1349) * subjective summarizer added * fix lint [Fix] Fix MathBench (#1351) Co-authored-by: liuhongwei <liuhongwei@pjlab.org.cn> [Update] Update model support list (#1353) * fix pip version * fix pip version * update model support subjective summarizer updated knowledge, math objective done (data need update) remove secrets objective changes saved knowledge data added * secrets removed * changed added * summarizer modified * summarizer modified * compassbench coding added * fix lint * objective summarizer updated * compass_bench_v1.3 updated * update files in config folder * remove unused model * lcbench modified * removed model evaluation configs * remove duplicated sdk implementation --------- Co-authored-by: zhangsongyang <zhangsongyang@pjlab.org.cn>
33 lines
1.2 KiB
Python
33 lines
1.2 KiB
Python
from opencompass.models import VLLM
|
|
|
|
settings = [
|
|
('llama-7b-vllm', 'huggyllama/llama-7b', 1),
|
|
('llama-13b-vllm', 'huggyllama/llama-13b', 1),
|
|
('llama-30b-vllm', 'huggyllama/llama-30b', 2),
|
|
('llama-65b-vllm', 'huggyllama/llama-65b', 4),
|
|
('llama-2-7b-vllm', 'meta-llama/Llama-2-7b-hf', 1),
|
|
('llama-2-13b-vllm', 'meta-llama/Llama-2-13b-hf', 1),
|
|
('llama-2-70b-vllm', 'meta-llama/Llama-2-70b-hf', 4),
|
|
('llama-3-8b-vllm', 'meta-llama/Meta-Llama-3-8B', 1),
|
|
('llama-3-70b-vllm', 'meta-llama/Meta-Llama-3-70B', 4),
|
|
('llama-3.1-8b-instruct-vllm', 'meta-llama/Meta-Llama-3.1-8B-Instruct', 1)
|
|
('llama-3.1-70b-instruct-vllm', 'meta-llama/Meta-Llama-3.1-70B-Instruct', 4)
|
|
('llama-3.1-405b-fp8-instruct-vllm', 'meta-llama/Meta-Llama-3.1-405B-Instruct-FP8', 8)
|
|
]
|
|
|
|
models = []
|
|
for abbr, path, num_gpus in settings:
|
|
models.append(
|
|
dict(
|
|
type=VLLM,
|
|
abbr=abbr,
|
|
path=path,
|
|
model_kwargs=dict(tensor_parallel_size=num_gpus),
|
|
max_out_len=100,
|
|
max_seq_len=2048,
|
|
batch_size=32,
|
|
generation_kwargs=dict(temperature=0),
|
|
run_cfg=dict(num_gpus=num_gpus, num_procs=1),
|
|
)
|
|
)
|