Hugging Face's logo

Pinkstack
/
SuperThoughts-CoT-14B-16k-o1-QwQ-GGUF

Text Generation
Transformers
GGUF
English
multilingual
phi3
text-generation-inference
unsloth
llama
code
cot
o1
reasoning
Eval Results
Inference Endpoints
conversational
Model card Files Community
1
Pinkstack commited on
Commit
f492c3f
·
verified ·
1 Parent(s): 8909dbb

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -31,7 +31,7 @@ widget:
31
  [Phi-4 Technical Report](https://arxiv.org/pdf/2412.08905) (SuperThoughts 14B is based on phi-4)
32
  # We are very proud to announce, SuperThoughts, but you can just call it o1 mini 😉
33
  Please check the examples we provided: https://huggingface.co/Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ-GGUF#%F0%9F%A7%80-examples
34
- ![PARM-2.png](https://cdn-uploads.huggingface.co/production/uploads/6710ba6af1279fe0dfe33afe/9wMB_c4WmaJR91f-ybFJl.png)
35
  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. This model is our new flagship. Please note that this is an experimental Cot model by us, if there are any issues report them! a system prompt is very important but it would do everything in two steps (Reasoning -> Final answer) regardless.
36
  # 🧀 Which quant is right for you? (all tested!)
37
  - ***Q3:*** This quant should be used on most high-end devices like rtx 2080TI's, Responses are very high quality, but its slightly slower than Q4. (Runs at ~1 tokens per second or less on a Samsung z fold 5 smartphone.)
 
31
  [Phi-4 Technical Report](https://arxiv.org/pdf/2412.08905) (SuperThoughts 14B is based on phi-4)
32
  # We are very proud to announce, SuperThoughts, but you can just call it o1 mini 😉
33
  Please check the examples we provided: https://huggingface.co/Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ-GGUF#%F0%9F%A7%80-examples
34
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6710ba6af1279fe0dfe33afe/QDHJhI0EVT_L9AHY_g3Br.png)
35
  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. This model is our new flagship. Please note that this is an experimental Cot model by us, if there are any issues report them! a system prompt is very important but it would do everything in two steps (Reasoning -> Final answer) regardless.
36
  # 🧀 Which quant is right for you? (all tested!)
37
  - ***Q3:*** This quant should be used on most high-end devices like rtx 2080TI's, Responses are very high quality, but its slightly slower than Q4. (Runs at ~1 tokens per second or less on a Samsung z fold 5 smartphone.)