FancyZhao eddyyeo commited on
Commit
9c1afe4
1 Parent(s): 5a596d5

Update README.md (#2)

Browse files

- Update README.md (cbfb21fc7811bfbadf99dca79bfc85b4b8b3518c)


Co-authored-by: Eddy Yeo <[email protected]>

Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -13,7 +13,7 @@ license_link: LICENSE
13
 
14
  ## Introduction
15
 
16
- The **Yi** series models are large language models trained from scratch by developers at [01.AI](https://01.ai/). The first public release contains two base models with the parameter size of 6B and 34B.
17
 
18
  ## News
19
 
@@ -36,9 +36,9 @@ The **Yi** series models are large language models trained from scratch by devel
36
  | **Yi-34B** | **76.3** | **83.7** | **81.4** | **82.8** | **54.3** | **80.1** | **76.4** | **37.1** |
37
 
38
 
39
- While benchmarking open-source models, we have observed a disparity between the results generated by our pipeline and those reported in public sources (e.g. OpenCampus). Upon conducting a more in-depth investigation of this difference, we have discovered that various models may employ different prompts, post-processing strategies, and sampling techniques, potentially resulting in significant variations in the outcomes. Our prompt and post-processing strategy remains consistent with the original benchmark, and greedy decoding is employed during evaluation without any post-processing for the generated content. For scores that did not report by original author (including score reported with different setting), we try to get results with our pipeline.
40
 
41
- To extensively evaluate model's capability, we adopted the methodology outlined in Llama2. Specifically, we included PIQA, SIQA, HellaSwag, WinoGrande, ARC, OBQA, and CSQA to assess common sense reasoning. SquAD, QuAC, and BoolQ were incorporated to evaluate reading comprehension. CSQA was exclusively tested using a 7-shot setup, while all other tests were conducted in a 0-shot configuration. Additionally, we introduced GSM8K (8-shot@1), MATH (4-shot@1), HumanEval (0-shot@1), and MBPP (3-shot@1) under the category "Math & Code". Due to technical constraints, we did not test Falcon-180 on QuAC and OBQA; the score is derived by averaging the scores on the remaining tasks. Since the scores for these two tasks are generally lower than the average, we believe that Falcon-180B's performance was not underestimated.
42
 
43
  ## Disclaimer
44
 
 
13
 
14
  ## Introduction
15
 
16
+ The **Yi** series models are large language models trained from scratch by developers at [01.AI](https://01.ai/). The first public release contains two base models with the parameter sizes of 6B and 34B.
17
 
18
  ## News
19
 
 
36
  | **Yi-34B** | **76.3** | **83.7** | **81.4** | **82.8** | **54.3** | **80.1** | **76.4** | **37.1** |
37
 
38
 
39
+ While benchmarking open-source models, we have observed a disparity between the results generated by our pipeline and those reported in public sources (e.g. OpenCompass). Upon conducting a more in-depth investigation of this difference, we have discovered that various models may employ different prompts, post-processing strategies, and sampling techniques, potentially resulting in significant variations in the outcomes. Our prompt and post-processing strategy remains consistent with the original benchmark, and greedy decoding is employed during evaluation without any post-processing for the generated content. For scores that were not reported by the original authors (including scores reported with different settings), we try to get results with our pipeline.
40
 
41
+ To evaluate the model's capability extensively, we adopted the methodology outlined in Llama2. Specifically, we included PIQA, SIQA, HellaSwag, WinoGrande, ARC, OBQA, and CSQA to assess common sense reasoning. SquAD, QuAC, and BoolQ were incorporated to evaluate reading comprehension. CSQA was exclusively tested using a 7-shot setup, while all other tests were conducted with a 0-shot configuration. Additionally, we introduced GSM8K (8-shot@1), MATH (4-shot@1), HumanEval (0-shot@1), and MBPP (3-shot@1) under the category "Math & Code". Due to technical constraints, we did not test Falcon-180 on QuAC and OBQA; the score is derived by averaging the scores on the remaining tasks. Since the scores for these two tasks are generally lower than the average, we believe that Falcon-180B's performance was not underestimated.
42
 
43
  ## Disclaimer
44