OpenCompass/configs/models/hf_llama/lmdeploy_llama3_8b_instruct.py

from opencompass.models import TurboMindModelwithChatTemplate

models = [
    dict(
        type=TurboMindModelwithChatTemplate,
        abbr='llama-3-8b-instruct-turbomind',
        path='meta-llama/Meta-Llama-3-8B-Instruct',
        engine_config=dict(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=16384,
        max_out_len=4096,
        batch_size=16,
        run_cfg=dict(num_gpus=1),
        stop_words=['<|end_of_text|>', '<|eot_id|>'],
    )
]