c38e18f2ff
* Move 1024 test just after 32-32 test; and enable all model for 1024-128 * Make sure python output encoding in utf-8 so that redirect to txt can always be success * Upload results to ftp * Small fix
24 lines
801 B
YAML
24 lines
801 B
YAML
repo_id:
|
|
- 'THUDM/chatglm2-6b'
|
|
- 'THUDM/chatglm3-6b'
|
|
- 'baichuan-inc/Baichuan2-7B-Chat'
|
|
- 'internlm/internlm-chat-7b-8k'
|
|
- 'Qwen/Qwen-7B-Chat'
|
|
- 'BAAI/AquilaChat2-7B'
|
|
- '01-ai/Yi-6B'
|
|
- 'meta-llama/Llama-2-7b-chat-hf'
|
|
- 'WisdomShell/CodeShell-7B-Chat'
|
|
- 'tiiuae/falcon-7b-instruct-with-patch'
|
|
- 'mosaicml/mpt-7b-chat'
|
|
- 'liuhaotian/llava-v1.5-7b'
|
|
- 'RWKV/rwkv-4-world-7b'
|
|
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)
|
|
in_out_pairs:
|
|
- '1024-128'
|
|
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)
|