scq21cs2dsadsa commited on
Commit
681ea5e
·
1 Parent(s): 0b134d4

Update benchmark scores to 3 decimal places in original README structure

Browse files
Files changed (1) hide show
  1. README.md +20 -19
README.md CHANGED
@@ -37,28 +37,28 @@ Beyond its improved reasoning capabilities, this version also offers a reduced h
37
 
38
  <div align="center">
39
 
40
- | Category | Benchmark | Score |
41
- |-------------------------|--------------------------|--------|
42
- | **Core Reasoning** | Math Reasoning | 0.875 |
43
- | | Logical Reasoning | 0.842 |
44
- | | Common Sense | 0.789 |
45
- | **Language Understanding** | Reading Comprehension | 0.815 |
46
- | | Question Answering | 0.763 |
47
- | | Text Classification | 0.851 |
48
- | | Sentiment Analysis | 0.822 |
49
- | **Generation** | Code Generation | 0.794 |
50
- | | Creative Writing | 0.736 |
51
- | | Dialogue Generation | 0.778 |
52
- | | Summarization | 0.803 |
53
- | **Specialized** | Translation | 0.837 |
54
- | | Knowledge Retrieval | 0.751 |
55
- | | Instruction Following | 0.864 |
56
- | | Safety Evaluation | 0.889 |
57
 
58
  </div>
59
 
60
  ### Overall Performance Summary
61
- The MyAwesomeModel demonstrates strong performance across all 15 evaluated benchmark categories, with particularly notable results in reasoning (Math: 0.875, Logical: 0.842) and safety evaluation (0.889). The model shows consistent improvements in complex task handling compared to previous versions.
62
 
63
  ## 3. Chat Website & API Platform
64
  We offer a chat interface and API for you to interact with MyAwesomeModel. Please check our official website for more details.
@@ -103,7 +103,7 @@ For web search enhanced generation, we recommend the following prompt template w
103
  search_answer_en_template = \
104
  '''# The following contents are the search results related to the user's message:
105
  {search_results}
106
- In the search results I provide to you, each result is formatted as [webpage X begin]...[webpage X end], where X represents the numerical index of each article. Please cite the context at the end of the relevant sentence when appropriate. Use the citation format [citation:X] in the corresponding part of your answer. If a sentence is derived from multiple contexts, list all relevant citation numbers, such as [citation:3][citation:5]. Be sure not to cluster all citations at the end; instead, include them in the corresponding parts of your answer.
107
  When responding, please keep the following points in mind:
108
  - Today is {cur_date}.
109
  - Not all content in the search results is closely related to the user's question. You need to evaluate and filter the search results based on the question.
@@ -123,3 +123,4 @@ This code repository is licensed under the [MIT License](LICENSE). The use of My
123
 
124
  ## 6. Contact
125
  If you have any questions, please raise an issue on our GitHub repository or contact us at contact@MyAwesomeModel.ai.
 
 
37
 
38
  <div align="center">
39
 
40
+ | | Benchmark | Model1 | Model2 | Model1-v2 | MyAwesomeModel |
41
+ |---|---|---|---|---|---|
42
+ | **Core Reasoning Tasks** | Math Reasoning | 0.510 | 0.535 | 0.521 | 0.875 |
43
+ | | Logical Reasoning | 0.789 | 0.801 | 0.810 | 0.842 |
44
+ | | Common Sense | 0.716 | 0.702 | 0.725 | 0.789 |
45
+ | **Language Understanding** | Reading Comprehension | 0.671 | 0.685 | 0.690 | 0.815 |
46
+ | | Question Answering | 0.582 | 0.599 | 0.601 | 0.763 |
47
+ | | Text Classification | 0.803 | 0.811 | 0.820 | 0.851 |
48
+ | | Sentiment Analysis | 0.777 | 0.781 | 0.790 | 0.822 |
49
+ | **Generation Tasks** | Code Generation | 0.615 | 0.631 | 0.640 | 0.794 |
50
+ | | Creative Writing | 0.588 | 0.579 | 0.601 | 0.736 |
51
+ | | Dialogue Generation | 0.621 | 0.635 | 0.639 | 0.778 |
52
+ | | Summarization | 0.745 | 0.755 | 0.760 | 0.803 |
53
+ | **Specialized Capabilities**| Translation | 0.782 | 0.799 | 0.801 | 0.837 |
54
+ | | Knowledge Retrieval | 0.651 | 0.668 | 0.670 | 0.751 |
55
+ | | Instruction Following | 0.733 | 0.749 | 0.751 | 0.864 |
56
+ | | Safety Evaluation | 0.718 | 0.701 | 0.725 | 0.889 |
57
 
58
  </div>
59
 
60
  ### Overall Performance Summary
61
+ The MyAwesomeModel demonstrates strong performance across all evaluated benchmark categories, with particularly notable results in reasoning and generation tasks.
62
 
63
  ## 3. Chat Website & API Platform
64
  We offer a chat interface and API for you to interact with MyAwesomeModel. Please check our official website for more details.
 
103
  search_answer_en_template = \
104
  '''# The following contents are the search results related to the user's message:
105
  {search_results}
106
+ In the search results I provide to you, each result is formatted as [webpage X begin]...[webpage X end], where X represents the numerical index of each article. Please cite the context at the end of the relevant sentence when appropriate. Use the citation format [citation:X] in the corresponding part of your answer. If a sentence is derived from multiple contexts, list all relevant citation numbers, such as [citation:3][citation:5]. Be sure not to cluster all citations at the end; instead, include them in the corresponding parts of the answer.
107
  When responding, please keep the following points in mind:
108
  - Today is {cur_date}.
109
  - Not all content in the search results is closely related to the user's question. You need to evaluate and filter the search results based on the question.
 
123
 
124
  ## 6. Contact
125
  If you have any questions, please raise an issue on our GitHub repository or contact us at contact@MyAwesomeModel.ai.
126
+ ```