6c75c689ea
* 1k-512 2k-512 baseline * add cpu stress test * update yaml name * update * update * clean up * test * update * update * update * test * update
20 lines
615 B
YAML
20 lines
615 B
YAML
repo_id:
|
|
- 'meta-llama/Llama-2-7b-chat-hf'
|
|
- 'meta-llama/Llama-2-13b-chat-hf'
|
|
- 'THUDM/chatglm2-6b'
|
|
- 'THUDM/chatglm3-6b'
|
|
- 'baichuan-inc/Baichuan2-7B-Chat'
|
|
- 'baichuan-inc/Baichuan2-13B-Chat'
|
|
- 'Qwen/Qwen-14B-Chat'
|
|
local_model_hub: '/models'
|
|
warm_up: 1
|
|
num_trials: 4
|
|
num_beams: 1 # default to greedy search
|
|
low_bit: 'sym_int4' # default to use 'sym_int4' (i.e. symmetric int4)
|
|
in_out_pairs:
|
|
- '1024-512'
|
|
- '2048-512'
|
|
test_api:
|
|
- "transformer_int4"
|
|
# - "transformer_int4_gpu" # on Intel GPU
|
|
cpu_embedding: False # whether put embedding to CPU (only avaiable now for gpu win related test_api)
|