eval_llama3_instruct_vllm.py

from mmengine.config import read_base

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") or k == 'datasets'], [])
work_dir = './outputs/llama3-instruct/'

from opencompass.models import VLLM


llama3_meta_template = dict(
    round=[
        dict(role="HUMAN", begin="<|begin_of_text|>user<|end_header_id|>\n\n", end="<|eot_id|>"),
        dict(role="BOT", begin="<|begin_of_text|>assistant<|end_header_id|>\n\n", end="<|eot_id|>", generate=True),
    ],
    eos_token_id=[128001, 128009],
)

models = [
    dict(
        type=VLLM,
        abbr="llama-3-8b-instruct-hf",
        path="Meta-Llama-3-8B-Instruct",
        model_kwargs=dict(tensor_parallel_size=1),
        meta_template=llama3_meta_template,
        max_out_len=100,
        max_seq_len=2048,
        batch_size=1,
        generation_kwargs=dict(temperature=0),
        run_cfg=dict(num_gpus=1, num_procs=1),  
    )
]