oltsy commited on
Commit
08674a3
·
verified ·
1 Parent(s): a51d84a

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -19,7 +19,7 @@ T-pro-it-2.0 is a model built upon the Qwen 3 model family and incorporates both
19
  ### 📚 Dataset
20
 
21
  Instruction Pre-Training:
22
- 40B tokens of instruction data, with about 20% focused on reasoning tasks.
23
 
24
  Supervised Fine-Tuning (SFT):
25
  ~500K high-quality and diverse instructions with balanced complexity. Reasoning tasks make up about 20% of the dataset.
 
19
  ### 📚 Dataset
20
 
21
  Instruction Pre-Training:
22
+ 40B tokens of instruction data, with one-third focused on reasoning tasks.
23
 
24
  Supervised Fine-Tuning (SFT):
25
  ~500K high-quality and diverse instructions with balanced complexity. Reasoning tasks make up about 20% of the dataset.