Update README.md

README.md

@@ -11,9 +11,10 @@ language:
 pipeline_tag: text-generation
 ---
 
-# Uploaded  model
+# Information
+## Here are things you should be aware of when using PARM models (Pinkstack Accuracy Reasoning Models) 🧀
 
-This model has gotten extra training parameters, We trained with [this](https://huggingface.co/datasets/gghfez/QwQ-LongCoT-130K-cleaned) dataset.
+This PARM is based on Phi 3.5 mini which has gotten extra training parameters so it would have similar outputs to O.1 Mini, We trained with [this](https://huggingface.co/datasets/gghfez/QwQ-LongCoT-130K-cleaned) dataset.
 
 To use this model, you must use a service which supports the GGUF file format.
 Additionaly, this is the Prompt Template, it uses the Phi-3 template.
@@ -25,7 +26,9 @@ Additionaly, this is the Prompt Template, it uses the Phi-3 template.
 {{ end }}<|assistant|>
 {{ .Response }}<|end|>
 
-Highly recommended to be used with a system prompt.
+Highly recommended to be used with a system prompt. 
+
+This model has been tested inside of MSTY. with 8,192 Max token output and 32,000 Context. Less context is completly fine too but it does like to use a lot of tokens for reasoning. 
 
 - **Developed by:** Pinkstack
 - **License:** apache-2.0