19 lines
682 B
YAML
19 lines
682 B
YAML
repo_id:
|
|
- 'THUDM/chatglm3-6b'
|
|
- 'THUDM/glm-4-9b-chat'
|
|
- 'baichuan-inc/Baichuan2-7B-Chat'
|
|
- 'baichuan-inc/Baichuan2-13B-Chat'
|
|
- 'meta-llama/Llama-2-7b-chat-hf'
|
|
- 'meta-llama/Llama-2-13b-chat-hf'
|
|
- 'meta-llama/Meta-Llama-3-8B-Instruct'
|
|
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_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)
|