Update README.md

README.md

@@ -2,8 +2,6 @@
 license: mit
 language:
 - en
-base_model:
-- openai/gpt-oss-20b
 pipeline_tag: text-generation
 library_name: transformers.js
 tags:
@@ -12,6 +10,8 @@ tags:
 - grpo
 - vae
 - pytorch
+base_model:
+- openai-community/gpt2
 ---
   <div id="app">
     <!-- TOP BAR -->
@@ -26,24 +26,26 @@ tags:
         <button id="invertBtn" class="btn-ghost">- **License**: Apache 2.0</button>
       </div>
 ---
-      
-# MICROD v1.0 by webXOS
+```  
+# MICROD v1.0 (micro-distill-grpo-vae)
 This model was made with the Micro Distillery app available at: 
 
+```
 webxos.netlify.app/MICROD
 
-    Model Distillation Training: Simulate GRPO optimization with VAE filtering for small LLMs (42M-345M params).
-    Policy Experimentation: Test group sizes, KL penalties, cache reuse for RLHF-like training.
-    VAE Filtering: Apply latent space compression to improve distillation quality.
-    Sandbox Testing: Execute safe Python code with feedback masking.
-    Export & Deployment: Generate deployable models for inference in various frameworks.
-    Offline Usage: PWA supports offline training simulation and exports.
+    -Model Distillation Training: Simulate GRPO optimization with VAE filtering for small LLMs (42M-345M params).
+    -Policy Experimentation: Test group sizes, KL penalties, cache reuse for RLHF-like training.
+    -VAE Filtering: Apply latent space compression to improve distillation quality.
+    -Sandbox Testing: Execute safe Python code with feedback masking.
+    -Export & Deployment: Generate deployable models for inference in various frameworks.
+    -Offline Usage: PWA supports offline training simulation and exports.
+```
 
 ## Model Description
 This is a distilled language model trained using Group Relative Policy Optimization (GRPO) with VAE filtering. 
-**MICROD v1.0** is a small template model designed to be built upon for custom ground up builds. It is distillated into a 
+**MICROD v1.0 (micro-distill-grpo-vae)** is a small template model designed to be built upon for custom ground up builds. It is distillated into a 
 small set of files the user can use to template their own agents. Designed for educational learning and micro scalling. 
-Use **MICROD V1.0** in your own custom projects and train it from the ground up.
+Use **MICROD V1.0 (micro-distill-grpo-vae)** in your own custom projects and train it from the ground up.
 
 ## Model Details
 - **Model type**: micro-distill-grpo-vae