ayo/ipex-llm
1
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 1

update several models for nightly perf test (#11643)

Browse source 
Co-authored-by: Yishuo Wang <yishuo.wang@intel.com>
This commit is contained in:
RyuKosei 2024-07-24 23:06:08 -07:00 committed by GitHub
parent 4499d25c26
commit 2fbd375a94
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
6 changed files with 16 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

5
python/llm/test/benchmark/arc-perf-test-batch2.yaml
View file

@ -8,9 +8,12 @@ repo_id:
- 'deepseek-ai/deepseek-coder-6.7b-instruct' - 'deepseek-ai/deepseek-coder-6.7b-instruct'
- 'THUDM/glm-4-9b-chat' - 'THUDM/glm-4-9b-chat'
- 'openbmb/MiniCPM-2B-sft-bf16' - 'openbmb/MiniCPM-2B-sft-bf16'
#- 'Qwen/Qwen-VL-Chat' - 'Qwen/Qwen-VL-Chat'
#- 'SmerkyG/rwkv-5-world-7b' #this model only fp32 is supported for now, fp16 and bf16 are not supported #- 'SmerkyG/rwkv-5-world-7b' #this model only fp32 is supported for now, fp16 and bf16 are not supported
- '01-ai/Yi-6B-Chat' - '01-ai/Yi-6B-Chat'
- 'mistralai/Mistral-7B-Instruct-v0.2'
- 'deepseek-ai/deepseek-coder-7b-instruct-v1.5'
- '01-ai/Yi-1.5-6B-Chat'
local_model_hub: '/mnt/disk1/models' local_model_hub: '/mnt/disk1/models'
warm_up: 1 warm_up: 1
num_trials: 3 num_trials: 3

7
python/llm/test/benchmark/arc-perf-test-batch4.yaml
View file

@ -8,9 +8,12 @@ repo_id:
- 'deepseek-ai/deepseek-coder-6.7b-instruct' - 'deepseek-ai/deepseek-coder-6.7b-instruct'
- 'THUDM/glm-4-9b-chat' - 'THUDM/glm-4-9b-chat'
- 'openbmb/MiniCPM-2B-sft-bf16' - 'openbmb/MiniCPM-2B-sft-bf16'
#- 'Qwen/Qwen-VL-Chat' - 'Qwen/Qwen-VL-Chat'
#- 'SmerkyG/rwkv-5-world-7b' #this model only fp32 is supported for now, fp16 and bf16 are not supported #- 'SmerkyG/rwkv-5-world-7b' #this model only fp32 is supported for now, fp16 and bf16 are not supported
- '01-ai/Yi-6B-Chat' - '01-ai/Yi-6B-Chat'
- 'mistralai/Mistral-7B-Instruct-v0.2'
- 'deepseek-ai/deepseek-coder-7b-instruct-v1.5'
- '01-ai/Yi-1.5-6B-Chat'
local_model_hub: '/mnt/disk1/models' local_model_hub: '/mnt/disk1/models'
warm_up: 1 warm_up: 1
num_trials: 3 num_trials: 3
@ -29,7 +32,7 @@ exclude:
- 'baichuan-inc/Baichuan2-7B-Chat:2048' - 'baichuan-inc/Baichuan2-7B-Chat:2048'
- 'baichuan-inc/Baichuan2-13B-Chat-4bit:1024' - 'baichuan-inc/Baichuan2-13B-Chat-4bit:1024'
- 'baichuan-inc/Baichuan2-13B-Chat-4bit:2048' - 'baichuan-inc/Baichuan2-13B-Chat-4bit:2048'
# - 'Qwen/Qwen-VL-Chat:2048' - 'Qwen/Qwen-VL-Chat:2048'
# - 'fnlp/moss-moon-003-sft-4bit:1024' # - 'fnlp/moss-moon-003-sft-4bit:1024'
# - 'fnlp/moss-moon-003-sft-4bit:2048' # - 'fnlp/moss-moon-003-sft-4bit:2048'
task: 'continuation' # task can be 'continuation', 'QA' and 'summarize' task: 'continuation' # task can be 'continuation', 'QA' and 'summarize'

5
python/llm/test/benchmark/arc-perf-test.yaml
View file

@ -8,9 +8,12 @@ repo_id:
- 'deepseek-ai/deepseek-coder-6.7b-instruct' - 'deepseek-ai/deepseek-coder-6.7b-instruct'
- 'THUDM/glm-4-9b-chat' - 'THUDM/glm-4-9b-chat'
- 'openbmb/MiniCPM-2B-sft-bf16' - 'openbmb/MiniCPM-2B-sft-bf16'
#- 'Qwen/Qwen-VL-Chat' - 'Qwen/Qwen-VL-Chat'
#- 'SmerkyG/rwkv-5-world-7b' #this model only fp32 is supported for now, fp16 and bf16 are not supported #- 'SmerkyG/rwkv-5-world-7b' #this model only fp32 is supported for now, fp16 and bf16 are not supported
- '01-ai/Yi-6B-Chat' - '01-ai/Yi-6B-Chat'
- 'mistralai/Mistral-7B-Instruct-v0.2'
- 'deepseek-ai/deepseek-coder-7b-instruct-v1.5'
- '01-ai/Yi-1.5-6B-Chat'
local_model_hub: '/mnt/disk1/models' local_model_hub: '/mnt/disk1/models'
warm_up: 1 warm_up: 1
num_trials: 3 num_trials: 3

1
python/llm/test/benchmark/arc-perf-transformers-437-batch2.yaml
View file

@ -5,6 +5,7 @@ repo_id:
- 'meta-llama/Meta-Llama-3-8B-Instruct' - 'meta-llama/Meta-Llama-3-8B-Instruct'
- 'microsoft/phi-3-vision-128k-instruct' - 'microsoft/phi-3-vision-128k-instruct'
- 'Qwen/Qwen2-7B-Instruct' - 'Qwen/Qwen2-7B-Instruct'
- 'microsoft/Phi-3-mini-128k-instruct'
local_model_hub: '/mnt/disk1/models' local_model_hub: '/mnt/disk1/models'
warm_up: 1 warm_up: 1
num_trials: 3 num_trials: 3

1
python/llm/test/benchmark/arc-perf-transformers-437-batch4.yaml
View file

@ -5,6 +5,7 @@ repo_id:
- 'meta-llama/Meta-Llama-3-8B-Instruct' # mwj: need to test - 'meta-llama/Meta-Llama-3-8B-Instruct' # mwj: need to test
- 'microsoft/phi-3-vision-128k-instruct' - 'microsoft/phi-3-vision-128k-instruct'
- 'Qwen/Qwen2-7B-Instruct' - 'Qwen/Qwen2-7B-Instruct'
- 'microsoft/Phi-3-mini-128k-instruct'
local_model_hub: '/mnt/disk1/models' local_model_hub: '/mnt/disk1/models'
warm_up: 1 warm_up: 1
num_trials: 3 num_trials: 3

1
python/llm/test/benchmark/arc-perf-transformers-437.yaml
View file

@ -5,6 +5,7 @@ repo_id:
- 'meta-llama/Meta-Llama-3-8B-Instruct' - 'meta-llama/Meta-Llama-3-8B-Instruct'
- 'microsoft/phi-3-vision-128k-instruct' - 'microsoft/phi-3-vision-128k-instruct'
- 'Qwen/Qwen2-7B-Instruct' - 'Qwen/Qwen2-7B-Instruct'
- 'microsoft/Phi-3-mini-128k-instruct'
local_model_hub: '/mnt/disk1/models' local_model_hub: '/mnt/disk1/models'
warm_up: 1 warm_up: 1
num_trials: 3 num_trials: 3