repo_id:
  - 'Qwen/Qwen1.5-7B-Chat'
  - 'meta-llama/Meta-Llama-3-8B-Instruct'
  - '01-ai/Yi-6B-Chat'
local_model_hub: 'path to your local model hub'
warm_up: 1
num_trials: 3
num_beams: 1 # default to greedy search
low_bit: 'sym_int4' # default to use 'sym_int4' (i.e. symmetric int4)
batch_size: 1 # default to 1
in_out_pairs:
  - '1024-128'
test_api:
  - "transformer_int4_fp16_gpu_win" # on Intel GPU for Windows, use fp16 for non-linear layer
cpu_embedding: True # whether put embedding to CPU (only avaiable now for gpu win related test_api)