p04798526
/
LLaMA-Factory-310P3
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

chore: add edited comand for mindie

This commit is contained in:
wql 2024-10-22 17:22:38 +08:00
parent 3f2f80db4d
commit 9ba88b0295
1 changed files with 13 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
mindie/tests/modeltest/README.md
View File

@ -50,6 +50,7 @@ source /usr/local/Ascend/nnal/atb/set_env.sh
source set_env.sh source set_env.sh
# 设置使用卡号 # 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="[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 或
export CUDA_VISIBLE_DEVICES="[卡号]" # GPU场景，如"0,1,2,3,4,5,6,7" 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 ## 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 [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 ##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]) 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 ##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 [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 ##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]) 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])