17 lines
592 B
YAML
17 lines
592 B
YAML
repo_id:
|
|
- 'Qwen/Qwen1.5-7B-Chat'
|
|
- 'meta-llama/Meta-Llama-3-8B-Instruct'
|
|
- '01-ai/Yi-6B-Chat'
|
|
- 'microsoft/phi-2'
|
|
- 'microsoft/Phi-3-mini-4k-instruct'
|
|
local_model_hub: 'path to your local model hub'
|
|
warm_up: 3
|
|
num_trials: 5
|
|
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:
|
|
- '32-32'
|
|
test_api:
|
|
- "transformer_int4_gpu_win" # on Intel GPU for Windows (catch GPU peak memory)
|
|
cpu_embedding: True # whether put embedding to CPU (only avaiable now for gpu win related test_api)
|