2685c41318
* Update 8192 prompt in all-in-one * Add cpu_embedding param for linux api * Update run.py * Update README.md
36 lines
1.5 KiB
YAML
36 lines
1.5 KiB
YAML
repo_id:
|
|
# - 'THUDM/chatglm2-6b'
|
|
- 'meta-llama/Llama-2-7b-chat-hf'
|
|
# - 'liuhaotian/llava-v1.5-7b' # requires a LLAVA_REPO_DIR env variables pointing to the llava dir; added only for gpu win related test_api now
|
|
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:
|
|
- '32-32'
|
|
- '1024-128'
|
|
test_api:
|
|
- "transformer_int4_gpu" # on Intel GPU
|
|
# - "transformer_int4_fp16_gpu" # on Intel GPU, use fp16 for non-linear layer
|
|
# - "ipex_fp16_gpu" # on Intel GPU
|
|
# - "bigdl_fp16_gpu" # on Intel GPU
|
|
# - "optimize_model_gpu" # on Intel GPU
|
|
# - "transformer_int4_gpu_win" # on Intel GPU for Windows
|
|
# - "transformer_int4_fp16_gpu_win" # on Intel GPU for Windows, use fp16 for non-linear layer
|
|
# - "transformer_int4_loadlowbit_gpu_win" # on Intel GPU for Windows using load_low_bit API. Please make sure you have used the save.py to save the converted low bit model
|
|
# - "deepspeed_optimize_model_gpu" # deepspeed autotp on Intel GPU
|
|
# - "speculative_gpu"
|
|
# - "transformer_int4"
|
|
# - "native_int4"
|
|
# - "optimize_model"
|
|
# - "pytorch_autocast_bf16"
|
|
# - "transformer_autocast_bf16"
|
|
# - "bigdl_ipex_bf16"
|
|
# - "bigdl_ipex_int4"
|
|
# - "bigdl_ipex_int8"
|
|
# - "speculative_cpu"
|
|
# - "deepspeed_transformer_int4_cpu" # on Intel SPR Server
|
|
cpu_embedding: False # whether put embedding to CPU
|
|
streaming: False # whether output in streaming way (only avaiable now for gpu win related test_api)
|