19 lines
655 B
YAML
19 lines
655 B
YAML
# For the models that require transformers 4.37.0
|
|
repo_id:
|
|
- 'Qwen/Qwen1.5-7B-Chat'
|
|
- 'microsoft/Phi-3-mini-4k-instruct'
|
|
- 'meta-llama/Meta-Llama-3-8B-Instruct'
|
|
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)
|
|
task: 'continuation' # task can be 'continuation', 'QA' and 'summarize'
|