64cfed602d
* Add new models to benchmark * remove Qwen/Qwen-VL-Chat to pass the validation --------- Co-authored-by: ATMxsp01 <shou.xu@intel.com>
31 lines
1.1 KiB
YAML
31 lines
1.1 KiB
YAML
repo_id:
|
|
- 'meta-llama/Llama-2-7b-chat-hf'
|
|
- 'meta-llama/Llama-2-13b-chat-hf'
|
|
- 'THUDM/chatglm3-6b-4bit'
|
|
- 'baichuan-inc/Baichuan2-7B-Chat'
|
|
- 'baichuan-inc/Baichuan2-13B-Chat-4bit'
|
|
- 'mistralai/Mistral-7B-v0.1'
|
|
- 'deepseek-ai/deepseek-coder-6.7b-instruct'
|
|
- 'THUDM/glm-4-9b-chat'
|
|
- 'openbmb/MiniCPM-2B-sft-bf16'
|
|
#- 'Qwen/Qwen-VL-Chat'
|
|
#- 'SmerkyG/rwkv-5-world-7b' #this model only fp32 is supported for now, fp16 and bf16 are not supported
|
|
- '01-ai/Yi-6B-Chat'
|
|
local_model_hub: '/mnt/disk1/models'
|
|
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:
|
|
- '32-32'
|
|
- '1024-128'
|
|
- '2048-256'
|
|
test_api:
|
|
- "transformer_int4_fp16_gpu" # on Intel GPU
|
|
cpu_embedding: False # whether put embedding to CPU (only avaiable now for gpu win related test_api)
|
|
exclude:
|
|
# - 'fnlp/moss-moon-003-sft-4bit:1024'
|
|
# - 'fnlp/moss-moon-003-sft-4bit:2048'
|
|
- 'baichuan-inc/Baichuan2-13B-Chat-4bit:2048'
|
|
task: 'continuation' # task can be 'continuation', 'QA' and 'summarize'
|