Henry94
/

Qwen1.5-7B-Character

Model card Files Files and versions Community

Henry94 commited on Nov 3, 2024

Commit

c6be423

·

verified ·

1 Parent(s): 1009683

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -37,8 +37,8 @@ To assess the efficacy of the Qwen1.5-7B-Character, we evaluated its performance
 | Model | ceval | cmmlu | mmlu |
 | :---: | :---: | :---: | :---: |
-| Qwen1.5-7B-filter     | 64.34| 64.48| 60.49|
 | Qwen1.5-7B            | 73.85| 73.29| 60.31|
 | Qwen1.5-7B-Character  | 67.24| 65.45| 59.99|
 In the table, to discern the model performance more distinctly, we have presented the test results for both the original Qwen1.5-7B (Qwen1.5-7B) and the token-modified Qwen1.5-7B (Qwen1.5-7B-filter).

 | Model | ceval | cmmlu | mmlu |
 | :---: | :---: | :---: | :---: |
 | Qwen1.5-7B            | 73.85| 73.29| 60.31|
+| Qwen1.5-7B-filter     | 64.34| 64.48| 60.49|
 | Qwen1.5-7B-Character  | 67.24| 65.45| 59.99|
 In the table, to discern the model performance more distinctly, we have presented the test results for both the original Qwen1.5-7B (Qwen1.5-7B) and the token-modified Qwen1.5-7B (Qwen1.5-7B-filter).