Update README.md

README.md

@@ -22,13 +22,13 @@ Minty is a non-profit organization that makes very small base and instruction-tu
 
 Our mission is to train models that can run on a wide range of hardware (including CPUs)!
 
-Currently, our models are trained on Google Colab, using Nvidia T4!
+Currently, our models are trained on Google Colab, using NVIDIA T4 GPUs!
 
 ## Future Plans
 
 | Model | Number of Parameters (and tokens, if applicable) | Variant | Will be Released on Minty Chat? |
 |---------|-------------|-------------|-------------|
-| Minty 1 Haiku | ~50M Parameters, ~3-5B Tokens | Base Model | No |
+| Minty 1 Haiku | ~50M Parameters, ~3–5B Tokens | Base Model | No |
 | Minty 1 Haiku Instruct | ~50M Parameters | Instruction-tuned Model | Yes |
 
 ## Other Future Plans
@@ -37,14 +37,17 @@ Currently, our models are trained on Google Colab, using Nvidia T4!
 
 A chat platform, powered by Minty models. You ask questions, it generates responses!
 
-### Planned Features:
+### Planned Features
+
 * ChatGPT-like UI
-* *(very future)* Model switcher
-* Web searching (so it can get latest info)
-* *(future)* Thinking mode (like in other models)
+* *(Very future)* Model switcher
+* Web searching (so it can access up-to-date information)
+* *(Future)* Thinking mode
 
 # Credits
+
 * Logo: Generated by Design.com AI (picked the best one).
 * Banner Design: Generated by GPT-5.6 Luna (and some minor edits by myself).
+* Readme Card: Written by myself and then rewritten with GPT-5.6 Luna.
 
 *by Mihai Popa, 2026*