ipex-llm/python/llm/test/benchmark/arc-perf-transformers-434.yaml
WeiguangHan 5098bc3544 LLM: enable previous models (#9505)
* enable previous models

* test mistral model

* for test

* run models separately

* test all models

* for test

* revert the llm_performance_test.yaml
2023-11-28 10:21:07 +08:00

14 lines
No EOL
371 B
YAML

# For the models that require transformers 4.34.0
repo_id:
- 'mistralai/Mistral-7B-v0.1'
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)
in_out_pairs:
- '32-32'
- '1024-128'
- '2048-256'
test_api:
- "transformer_int4_gpu" # on Intel GPU