22 lines
678 B
Python
22 lines
678 B
Python
from opencompass.models import HuggingFaceCausalLM
|
|
|
|
|
|
models = [
|
|
dict(
|
|
type=HuggingFaceCausalLM,
|
|
abbr='llama-2-70b-hf',
|
|
path="meta-llama/Llama-2-70b-hf",
|
|
tokenizer_path='meta-llama/Llama-2-70b-hf',
|
|
tokenizer_kwargs=dict(padding_side='left',
|
|
truncation_side='left',
|
|
use_fast=False,
|
|
),
|
|
max_out_len=100,
|
|
max_seq_len=2048,
|
|
batch_size=8,
|
|
model_kwargs=dict(device_map='auto'),
|
|
batch_padding=False, # if false, inference with for-loop without batch padding
|
|
run_cfg=dict(num_gpus=8, num_procs=1),
|
|
)
|
|
]
|