Pinkstack commited on
Commit
226f391
·
verified ·
1 Parent(s): 0cee8fd

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -1
README.md CHANGED
@@ -131,7 +131,10 @@ model-index:
131
  # We are very proud to announce, SuperThoughts, but you can just call it o1 mini 😉
132
  Please check the examples we provided: https://huggingface.co/Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ-GGUF#%F0%9F%A7%80-examples
133
  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6710ba6af1279fe0dfe33afe/QDHJhI0EVT_L9AHY_g3Br.png)
134
-
 
 
 
135
 
136
  Unlike previous models we've uploaded, this one is the best one we've published! Answers in two steps: Reasoning -> Final answer like o1 mini and other similar reasoning ai models.
137
  # 🧀 Which quant is right for you? (all tested!)
 
131
  # We are very proud to announce, SuperThoughts, but you can just call it o1 mini 😉
132
  Please check the examples we provided: https://huggingface.co/Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ-GGUF#%F0%9F%A7%80-examples
133
  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6710ba6af1279fe0dfe33afe/QDHJhI0EVT_L9AHY_g3Br.png)
134
+ Beats qwen/qwq at MATH & MuSR (MuSR being a reasoning benchmark)
135
+ Evaluation:
136
+ ![eval](https://cdn-uploads.huggingface.co/production/uploads/6710ba6af1279fe0dfe33afe/Dk-HD4wrS54r0lYlOF1Bz.png)
137
+ Please note, the low IFEVAL results is most likely due to the model always providing reasoning, prompt following is not great with this model sadly.
138
 
139
  Unlike previous models we've uploaded, this one is the best one we've published! Answers in two steps: Reasoning -> Final answer like o1 mini and other similar reasoning ai models.
140
  # 🧀 Which quant is right for you? (all tested!)