sh2orc commited on
Commit
9d9be38
·
verified ·
1 Parent(s): 66c7670

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -3
README.md CHANGED
@@ -33,12 +33,10 @@ pipeline_tag: text-generation
33
  The Qwen3-Coder-30B model shows specialized strength in mathematical reasoning tasks (GSM-8K) where it significantly outperforms the larger models. However, it lags behind the 235B models in general knowledge (MMLU), commonsense reasoning (Hellaswag), and pronoun disambiguation (Winogrande). This suggests the 30B model may have been optimized specifically for coding and mathematical tasks at the expense of some general capabilities.
34
 
35
 
 
36
 
37
 
38
  # Qwen3-Coder-30B-A3B-Instruct
39
- <a href="https://chat.qwen.ai/" target="_blank" style="margin: 2px;">
40
- <img alt="Chat" src="https://img.shields.io/badge/%F0%9F%92%9C%EF%B8%8F%20Qwen%20Chat%20-536af5" style="display: inline-block; vertical-align: middle;"/>
41
- </a>
42
 
43
  ## Highlights
44
 
 
33
  The Qwen3-Coder-30B model shows specialized strength in mathematical reasoning tasks (GSM-8K) where it significantly outperforms the larger models. However, it lags behind the 235B models in general knowledge (MMLU), commonsense reasoning (Hellaswag), and pronoun disambiguation (Winogrande). This suggests the 30B model may have been optimized specifically for coding and mathematical tasks at the expense of some general capabilities.
34
 
35
 
36
+ -----
37
 
38
 
39
  # Qwen3-Coder-30B-A3B-Instruct
 
 
 
40
 
41
  ## Highlights
42