natas_hw
/
openvino
0
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

[DOCS] benchmark fix table (#23062)

This commit is contained in:
Karol Blaszczak 2024-02-23 20:19:17 +01:00 committed by GitHub
parent 381a550f74
commit 7fe8b03cba
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 29 additions and 33 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

62
docs/articles_en/about_openvino/performance_benchmarks/performance_int8_vs_fp32.rst
View File

@ -5,12 +5,12 @@ Model Accuracy
The following two tables present the absolute accuracy drop calculated as the accuracy difference
between OV-accuracy and the original frame work accuracy for FP32, and the same for INT8, BF16 and
FP16 representations of a model on three platform architectures. Please also refer to notes below
The following two tables present the absolute accuracy drop calculated as the accuracy difference
between OV-accuracy and the original frame work accuracy for FP32, and the same for INT8, BF16 and
FP16 representations of a model on three platform architectures. Please also refer to notes below
The following two tables present the absolute accuracy drop calculated as the accuracy difference
between OV-accuracy and the original frame work accuracy for FP32, and the same for INT8, BF16 and
FP16 representations of a model on three platform architectures. Please also refer to notes below
The following two tables present the absolute accuracy drop calculated as the accuracy difference
between OV-accuracy and the original frame work accuracy for FP32, and the same for INT8, BF16 and
FP16 representations of a model on three platform architectures. Please also refer to notes below
the table for more information.
* A - Intel® Core™ i9-9000K (AVX2), INT8 and FP32
@ -108,32 +108,28 @@ the table for more information.
* - chatGLM2-6b
- lambada openai
- ppl
-
-
- 17.38
- 17.41
- 17.17
-
- 17.37 (ref. 17.48)
- 17.41 (ref. 17.48)
- 17.16 (ref. 17.48)
* - Llama-2-7b-chat
- Wiki, StackExch, Crawl
- ppl
-
-
- 3.24
- 3.24
- 3.25
- 3.25
* - Stable-Diffusion-V2-1
- LIAON-5B
- CLIP
-
-
-
-
-
-
-
-
* - Mistral-7b
- proprietary Mistral.ai
- ppl
-
-
- 3.29
- 3.47
- 3.49
@ -240,37 +236,37 @@ the table for more information.
* - chatGLM2-6b
- lambada openai
- ppl
-
-
- 17.48
- 17.56
-
-
- 17.49
* - Llama-2-7b-chat
- Wiki, StackExch, Crawl
- ppl
-
-
- 3.26
- 3.26
-
-
-
-
* - Stable-Diffusion-V2-1
- LIAON-5B
- CLIP
-
-
-
-
- 22.48
-
-
-
-
- 22.48
* - Mistral-7b
- proprietary Mistral.ai
- ppl
-
-
- 3.19
- 3.18
-
-
-
-
Notes: For all accuracy metrics except perplexity a "-", (minus sign), indicates an accuracy drop.
For perplexity (ppl) the values do not indicate a deviation from a reference but are the actual measured
Notes: For all accuracy metrics except perplexity a "-", (minus sign), indicates an accuracy drop.
For perplexity (ppl) the values do not indicate a deviation from a reference but are the actual measured
accuracy for the model.