"git@developer.sourcefind.cn:yangql/composable_kernel-1.git" did not exist on "c10a6e8293ade863a9b177de956d31eb86f4b128"
Commit 8b3db123 authored by gaoqiong's avatar gaoqiong
Browse files

修改lmdeploy相关的config

parent fb53af18
...@@ -75,7 +75,7 @@ python run.py configs/eval_llama2_vllm.py ...@@ -75,7 +75,7 @@ python run.py configs/eval_llama2_vllm.py
2、使用lmdeploy推理验证 2、使用lmdeploy推理验证
```shell ```shell
python run.py configs/eval_llama2_lmdelpoy.py python run.py configs/eval_llama2_lmdeploy.py
``` ```
3、使用tgi推理验证 3、使用tgi推理验证
......
from mmengine.config import read_base
from opencompass.models.turbomind import TurboMindModel
with read_base():
from .datasets.ARC_c.ARC_c_gen_1e0de5 import ARC_c_datasets
from .datasets.ARC_e.ARC_e_gen_1e0de5 import ARC_e_datasets
from .summarizers.example import summarizer
datasets = sum((v for k, v in locals().items() if k.endswith('_datasets')), [])
work_dir = './outputs/llama2/'
llama_chat_meta_template = dict(
round=[
dict(role="HUMAN", begin='[INST] ', end=' [/INST]'),
dict(role="BOT", begin=' ', end=' ', generate=True),
],
)
models = [
dict(
type=TurboMindModel,
abbr='llama-2-7b-hf-lmdeploy',
path="Llama-2-7b-hf",
engine_config=dict(session_len=4096,
max_batch_size=32,
rope_scaling_factor=1.0),
gen_config=dict(top_k=1,
top_p=0.8,
temperature=1.0,
max_new_tokens=100),
max_out_len=100,
max_seq_len=2048,
batch_size=1,
concurrency=1,
run_cfg=dict(num_gpus=1, num_procs=1)
)
]
\ No newline at end of file
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment