Update README.md

README.md

@@ -24,7 +24,7 @@ pipeline_tag: text-generation
 - ***Q4:*** This model should be used on edge devices like high end phones or laptops due to its very compact size, quality is okay but fully usable. 
 - ***Q8:*** This model should be used on most high end modern devices like rtx 3080, Responses are very high quality, but its noticeably slower than q4
 
-This Parm v2 is based on Qwen 2.5 3B which has gotten many extra reasoning training parameters so it would have similar outputs to qwen QwQ / O.1 mini (only much, smaller.), We trained using [this](https://huggingface.co/datasets/gghfez/QwQ-LongCoT-130K-cleaned) dataset, opus dataset and sonnet 3.5 dataset from huggingface.
+This Parm v2 is based on Qwen 2.5 3B which has gotten many extra reasoning training parameters so it would have similar outputs to qwen QwQ / O.1 mini (only much, smaller.). We've trained it using the datasets [here](https://huggingface.co/collections/Pinkstackorg/pram-v2-67612d3c542b9121bf15891c)
 
 This is a pretty heavy to run model if you want on device ai's for phones I'd recommend using the 0.5B version of this model (coming soon)