diff --git a/mindie/tests/modeltest/README.md b/mindie/tests/modeltest/README.md index 436b4eef..e83ede14 100644 --- a/mindie/tests/modeltest/README.md +++ b/mindie/tests/modeltest/README.md @@ -50,6 +50,7 @@ source /usr/local/Ascend/nnal/atb/set_env.sh source set_env.sh # 设置使用卡号 export ASCEND_RT_VISIBLE_DEVICES="[卡号]" # NPU场景,如"0,1,2,3,4,5,6,7" +export ASCEND_RT_VISIBLE_DEVICES="0,1,2,3,4,5,6,7" 或 export CUDA_VISIBLE_DEVICES="[卡号]" # GPU场景,如"0,1,2,3,4,5,6,7" ``` @@ -103,6 +104,16 @@ pip install -r requirements.txt ## 单机场景 bash run.sh pa_fp16 performance [case_pair] [batch_size] [model_name] ([is_chat_model]) [weight_dir] [chip_num] ([max_position_embedding/max_sequence_length]) +bash run.sh pa_fp16 performance [[256,256]] 1 qwen /home/user/repo/LLaMA-Factory-310P3/ms_cache/hub/qwen/Qwen-7B 8 +bash run.sh pa_fp16 performance [[256,256]] 1 qwen /home/user/repo/LLaMA-Factory-310P3/ms_cache/hub/qwen/Qwen-7B 1 +bash run.sh pa_fp16 performance [[256,256]] 1 llama /home/user/repo/LLaMA-Factory-310P3/ms_cache/hub/modelscope/llama-2-7b-ms 8 +bash run.sh pa_fp16 performance [[256,256]] 1 llama /home/user/repo/LLaMA-Factory-310P3/ms_cache/hub/modelscope/llama-2-7b-ms 1 +bash run.sh pa_fp16 performance [[256,256]] 1 chatglm2_6b /home/user/repo/LLaMA-Factory-310P3/ms_cache/hub/zhipuai/chatglm2-6b 8 +bash run.sh pa_fp16 performance [[256,256]] 1 chatglm2_6b /home/user/repo/LLaMA-Factory-310P3/ms_cache/hub/zhipuai/chatglm2-6b 1 +bash run.sh pa_fp16 performance [[256,256]] 1 baichuan2_7b /home/user/repo/LLaMA-Factory-310P3/ms_cache/hub/baichuan-inc/Baichuan2-7B-Base 8 +bash run.sh pa_fp16 performance [[256,256]] 1 baichuan2_7b /home/user/repo/LLaMA-Factory-310P3/ms_cache/hub/baichuan-inc/Baichuan2-7B-Base 1 + + ##多机场景 bash run.sh pa_fp16 performance [case_pair] [batch_size] [model_name] ([is_chat_model]) [weight_dir] [rank_table_file] [world_size] [node num] [rank_id_start] ([max_position_embedding/max_sequence_length]) @@ -161,6 +172,8 @@ bash run.sh pa_fp16 performance_maxbs [case_pair] [batch_range] [time_limit] [mo ##单机场景 bash run.sh pa_fp16 [dataset] ([shots]) [batch_size] [model_name] ([is_chat_model]) [weight_dir] [chip_num] ([max_position_embedding/max_sequence_length]) +bash run.sh pa_fp16 full_MMLU 0 1 qwen /home/user/repo/LLaMA-Factory-310P3/ms_cache/hub/qwen/Qwen-7B 8 + ##多机场景 bash run.sh pa_fp16 [dataset] ([shots]) [batch_size] [model_name] ([is_chat_model]) [weight_dir] [rank_table_file] [world_size] [node num] [rank_id_start] ([max_position_embedding/max_sequence_length])