amd
/

Safetensors
qwen3
llmll commited on
Commit
b639a6f
Β·
verified Β·
1 Parent(s): c0ac4f4

Upload folder using huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -16,7 +16,7 @@ license: apache-2.0
16
  </p>
17
 
18
 
19
- * **ReasonLite is an ultra-lightweight math reasoning model.** With only 0.6B parameters, it leverages **high-quality data distillation** to achieve performance comparable to models over 10Γ— its size, such as Qwen3-8B, **reaching 75.2 on AIME24 and extending the scaling law of small models.**
20
 
21
  * πŸ”₯ **Best-performing 0.6B reasoning model**
22
  * πŸ”“ Fully open-source β€” weights, scripts, datasets, synthesis pipeline
 
16
  </p>
17
 
18
 
19
+ **ReasonLite is an ultra-lightweight math reasoning model.** With only 0.6B parameters, it leverages **high-quality data distillation** to achieve performance comparable to models over 10Γ— its size, such as Qwen3-8B, **reaching 75.2 on AIME24 and extending the scaling law of small models.**
20
 
21
  * πŸ”₯ **Best-performing 0.6B reasoning model**
22
  * πŸ”“ Fully open-source β€” weights, scripts, datasets, synthesis pipeline