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

Removed no longer needed models for Arc nightly perf (#11722)

Browse source 
* removed LLMs that are no longer needed

Removed: 
mistralai/Mistral-7B-v0.1
deepseek-ai/deepseek-coder-6.7b-instruct

* Update arc-perf-test-batch4.yaml

Removed: 
deepseek-ai/deepseek-coder-6.7b-instruct
mistralai/Mistral-7B-v0.1

* Update arc-perf-test.yaml

Removed: 
deepseek-ai/deepseek-coder-6.7b-instruct
mistralai/Mistral-7B-v0.1

* Create arc-perf-transformers-438.yaml

* Moved arc-perf-transformers-438.yaml location

* Create arc-perf-transformers-438-batch2.yaml

* Create arc-perf-transformers-438-batch4.yaml

* Delete python/llm/test/benchmark/arc-perf-transformers-438-batch2.yaml

* Delete python/llm/test/benchmark/arc-perf-transformers-438-batch4.yaml

* Delete python/llm/test/benchmark/arc-perf-transformers-438.yaml
This commit is contained in:
SichengStevenLi 2024-08-06 16:12:00 +08:00 committed by GitHub
parent 929675aa6b
commit 985213614b
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 1 additions and 7 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
python/llm/test/benchmark/arc-perf-test-batch2.yaml
View file

@ -4,8 +4,6 @@ repo_id:
- 'THUDM/chatglm3-6b-4bit'
- 'baichuan-inc/Baichuan2-7B-Chat'
- 'baichuan-inc/Baichuan2-13B-Chat-4bit'
- 'mistralai/Mistral-7B-v0.1'
- 'deepseek-ai/deepseek-coder-6.7b-instruct'
- 'THUDM/glm-4-9b-chat'
- 'openbmb/MiniCPM-2B-sft-bf16'
- 'Qwen/Qwen-VL-Chat'
@ -29,4 +27,4 @@ test_api:
cpu_embedding: False # whether put embedding to CPU (only avaiable now for gpu win related test_api)
exclude:
- 'baichuan-inc/Baichuan2-13B-Chat-4bit:2048'
task: 'continuation' # task can be 'continuation', 'QA' and 'summarize'
task: 'continuation' # task can be 'continuation', 'QA' and 'summarize'

2
python/llm/test/benchmark/arc-perf-test-batch4.yaml
View file

@ -4,8 +4,6 @@ repo_id:
- 'THUDM/chatglm3-6b-4bit'
- 'baichuan-inc/Baichuan2-7B-Chat'
- 'baichuan-inc/Baichuan2-13B-Chat-4bit'
- 'mistralai/Mistral-7B-v0.1' #mwj: need to check
- 'deepseek-ai/deepseek-coder-6.7b-instruct'
- 'THUDM/glm-4-9b-chat'
- 'openbmb/MiniCPM-2B-sft-bf16'
- 'Qwen/Qwen-VL-Chat'

2
python/llm/test/benchmark/arc-perf-test.yaml
View file

@ -4,8 +4,6 @@ repo_id:
- 'THUDM/chatglm3-6b-4bit'
- 'baichuan-inc/Baichuan2-7B-Chat'
- 'baichuan-inc/Baichuan2-13B-Chat-4bit'
- 'mistralai/Mistral-7B-v0.1'
- 'deepseek-ai/deepseek-coder-6.7b-instruct'
- 'THUDM/glm-4-9b-chat'
- 'openbmb/MiniCPM-2B-sft-bf16'
- 'Qwen/Qwen-VL-Chat'