Update README.md

README.md

@@ -1,11 +1,11 @@
 ---
 license: apache-2.0
 ---
-# Art-0-8B: _Reasoning the way you want it to with Adaptive Thinking_
+# CustomThinker-0-8B: _Reasoning the way you want it to_
 
-**[Join Our Community](https://agi-0.com)**
+> If you want to contact me about this experiment, consulting, or anything else you can find my email at https://gr.bio
 
-Art-0-8B is the first open-source LLM that allows users to explicitly control its reasoning methodology through direct prompting instructions.
+CustomThinker-0-8B is the first open-source LLM that allows users to explicitly control its reasoning methodology through direct prompting instructions.
 
 This experimental model is fine-tuned on Qwen3-8B using a specialized dataset that makes the model's thinking style directly controllable through system prompts, similar to how you would instruct an LLM to adopt a specific persona or output format.
 
@@ -21,20 +21,20 @@ Reasoning Instructions:
 
 While the model is primarily trained to implement adaptive thinking based on system prompt instructions, it can also respond to reasoning style changes requested during mid-conversation, though this functionality may not be consistently reliable.
 
-Some of the benefits that Adaptive Thinking enables:
+Some of the benefits that this strategy enables:
 
 - Direct control over AI reasoning patterns and output structure
 - Enhanced experimentation with reasoning models and potential for RL strategies that optimize thinking styles
 - Improved safety through explicit control over the reasoning process
 - Customizable thinking approaches tailored to specific tasks
 
-While prompt engineering has long been known to improve LLM performance, Art-0 represents the first approach that gives users direct control over the internal reasoning process of LLMs. This capability allows models to be configured with optimal thinking patterns for different use cases.
+While prompt engineering has long been known to improve LLM performance, CustomThinker represents the first approach that gives users direct control over the internal reasoning process of LLMs. This capability allows models to be configured with optimal thinking patterns for different use cases.
 
 _If you like this, please consider leaving a like on the repository—it would help us, and if you can, also leave feedback in the community section._
 
 ## 🎯 See Art in Action
 
-[**→ Try more examples in our interactive demo**](https://huggingface.co/spaces/gr0010/Try-Art-0-8B)
+[**→ Try more examples in our interactive demo**](https://huggingface.co/spaces/gr0010/CustomThinker-Demo)
 ### Example: Thinking in Rap Lyrics
 
 **System Prompt:**
@@ -123,14 +123,14 @@ The number of R's in "raspberry" is 3. The fourth prime number is 7. Multiplying
 **Answer: 441**
 ```
 
-[**→ Try more examples in our interactive demo**](https://huggingface.co/spaces/gr0010/Try-Art-0-8B)
+[**→ Try more examples in the interactive demo**](https://huggingface.co/spaces/gr0010/Try-Art-0-8B)
 
 ## 🚀 Quick Start
 
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
-model_name = "AGI-0/Art-0-8B"
+model_name = "gr0010/CustomThinker-0-8B"
 
 # load the tokenizer and the model
 tokenizer = AutoTokenizer.from_pretrained(model_name)