ipex-llm/python/llm/test/benchmark/arc-perf-test.yaml

17 lines
388 B
YAML

repo_id:
- 'THUDM/chatglm2-6b'
- 'meta-llama/Llama-2-7b-chat-hf'
- 'meta-llama/Llama-2-13b-chat-hf'
- 'tiiuae/falcon-7b-instruct-with-patch'
- 'mosaicml/mpt-7b-chat'
local_model_hub: '/mnt/disk1/models'
warm_up: 1
num_trials: 3
num_beams: 1 # default to greedy search
in_out_pairs:
- '32-32'
- '1024-128'
- '2048-256'
test_api:
- "transformer_int4_gpu" # on Intel GPU