amang1802
/

llama-3.1-70B-cpttest_mode2_qna_fulltext

Model card Files Files and versions Community

amang1802 commited on Jan 7

Commit

16e8aad

·

verified ·

1 Parent(s): 0874cb4

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -7,7 +7,7 @@ base_model:
 ---
 - Trained using torchtune for CPT testing
-- Shows a good improvement in Ground Truth Accuracy when using Q&A dataset instead of just wiki like text: 36% to 51%
 - Curiously, uses the Question/Answer format for generating content even though the few shot prompt showed standard paragraph style text
 ---

 ---
 - Trained using torchtune for CPT testing
+- Shows a good improvement in Ground Truth Accuracy when using Q&A dataset instead of just wiki like text: 37% to 51%
 - Curiously, uses the Question/Answer format for generating content even though the few shot prompt showed standard paragraph style text
 ---