User01110 commited on
Commit
da7371f
·
verified ·
1 Parent(s): 35180ad

Clarify embedded Qwen3Config

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -119,4 +119,4 @@ with torch.no_grad():
119
  print(tokenizer.decode(output[0], skip_special_tokens=True))
120
  ```
121
 
122
- This repo uses self-contained Transformers remote code with a Qwen3-style dense decoder and a math-only novelty-gated attention block.
 
119
  print(tokenizer.decode(output[0], skip_special_tokens=True))
120
  ```
121
 
122
+ This repo uses a self-contained remote `Qwen3Config` plus model code for a Qwen3-style dense decoder with a math-only novelty-gated attention block.