Update README.md

README.md

@@ -6,7 +6,7 @@ base_model:
 - meta-llama/Llama-3.2-3B-Instruct
 ---
 
-# Gladiator-Mini-exp-1211: A Compact and Powerful Reasoning Engine
+# Gladiator-Mini-exp-1211
 
 **Gladiator-Mini-exp-1211** is a 3-billion parameter language model designed for **complex reasoning tasks**. This experimental model, based on [meta-llama/Llama-3.2-3B-Instruct] [https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct], offers surprisingly strong analytical capabilities for its size. It demonstrates the potential of smaller models to achieve impressive performance in analytical thinking. We chose to finetune on a Llama model due to finetuning difficulties with the Qwen 2.5 3B model.
 
@@ -27,6 +27,8 @@ Gladiator-Mini-exp-1211 works best with **carefully crafted system prompts** tha
 **Why is it "Experimental"?**
 
 Gladiator-Mini-exp-1211 is still under development (hence the "exp" in its name). It may have biases, limitations, and areas where its reasoning is not yet perfect. We're releasing it to the community to gather feedback, explore its full capabilities, and continue to improve it. The experimental date is 12/11/2024.
+**Note: This is an experimental model, and its performance may vary compared to the base model. We are unsure.**
+
 
 **The Goal:**
 
@@ -48,4 +50,6 @@ Gladiator-Mini-exp-1211 is an experimental model and should be used with caution
 
 Base model: https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct
 
-Thanks to Meta for the fantastic Llama-3.2-3B model!
+Thanks to Meta for the fantastic Llama-3.2-3B model!
+
+Newer experimental models will bring hopefully smarter models.