Update README.md

README.md

@@ -44,13 +44,13 @@ This model was produced with **Micro Distillery v2.5** — a single-file HTML PW
 Available for download in the repo folder. [Here](https://huggingface.co/webxos/microd-bigram-v2/tree/main/micro-distillery-pwa). This is an experimental, all-in-one development environment that runs completely inside a web browser. It is built as a single-file HTML Progressive Web App (PWA), meaning it operates locally on your machine, requires no server-side backend, and can even work offline once loaded.
 
 
-Key Features of Micro Distillery v2.5
+## Key Features of Micro Distillery v2.5
 
-• In-Browser Training Pipeline: It fetches open text datasets (like Andrej Karpathy's names.txt), counts character pairs to build a 27×27 transition table, and optimizes the paths using a basic, rule-based reinforcement loop.
-• Fan-Out NLP Polish (v2): The app includes a post-processing dashboard where you can hook up external text APIs. It features daily quota tracking for MyMemory (for translation/paraphrasing), Datamuse integration for lexical scoring, and configuration toggles for LanguageTool grammar checkers.
-• Jev Code (Nous Deterministic Layer): It features a local, network-free code harness modal. It simulates a strict, token-by-token code prediction pipeline (tokenize → context → candidates → score → select → validate) with a built-in user confirmation popup before accepting predictions.
-• Hugging Face Bundler: Once you are done experimenting in the browser, the app automatically generates a complete, standards-compliant .zip bundle. This bundle includes everything needed to host the project on Hugging Face: the structural configurations (config.json, vocab.json), interactive Python test wrappers (test.py), a formatted model card (README.md), and even pipeline architecture vector diagrams (pipeline.svg).
-• Safe State Guards: To keep the browser from freezing during asynchronous tasks, the app implements strict mutual exclusion locks (state.training and state.fetching) to ensure data pulling and model training never overlap and crash the tab.
+- • In-Browser Training Pipeline: It fetches open text datasets (like Andrej Karpathy's names.txt), counts character pairs to build a 27×27 transition table, and optimizes the paths using a basic, rule-based reinforcement loop.
+- • Fan-Out NLP Polish (v2): The app includes a post-processing dashboard where you can hook up external text APIs. It features daily quota tracking for MyMemory (for translation/paraphrasing), Datamuse integration for lexical scoring, and configuration toggles for LanguageTool grammar checkers.
+- • Jev Code (Nous Deterministic Layer): It features a local, network-free code harness modal. It simulates a strict, token-by-token code prediction pipeline (tokenize → context → candidates → score → select → validate) with a built-in user confirmation popup before accepting predictions.
+- • Hugging Face Bundler: Once you are done experimenting in the browser, the app automatically generates a complete, standards-compliant .zip bundle. This bundle includes everything needed to host the project on Hugging Face: the structural configurations (config.json, vocab.json), interactive Python test wrappers (test.py), a formatted model card (README.md), and even pipeline architecture vector diagrams (pipeline.svg).
+- • Safe State Guards: To keep the browser from freezing during asynchronous tasks, the app implements strict mutual exclusion locks (state.training and state.fetching) to ensure data pulling and model training never overlap and crash the tab.
 
 ## CHANGE LOG — Updated 2026-10-25