Update README.md

README.md

@@ -2,9 +2,25 @@
 license: mit
 ---
 
-# Lethe AI Sharp
+# Repo Information
 
-This repo contains useful content for the [Lethe AI Sharp](https://github.com/SerialKicked/Lethe-AI-Sharp/) library. It is a modular, object‑oriented C# library that connects local or remote Large Language Model (LLM) backends to your applications (desktop tools, game engines, services). It also comes with its own light backend, allowing you to run a local LLM in the GGUF format directly without even having to rely on anything else.
+This repo contains useful content for the [Lethe AI Sharp](https://github.com/SerialKicked/Lethe-AI-Sharp/) library: classification models, fixed jinja templates, and other files. More information about the library below.
+
+## Fixed Jinja Templates
+
+This repo also contains fixed (and more permissive) Jinja templates for Mistral (Tekken7) and Qwen 3.5 (ChatML) models. They allow for system messages mid conversations (requirement for LetheAI) while other so-called errors that could trigger when using those LLM in way not initially intended.
+
+## gte-large.Q6_K.gguf
+
+A Q6_K quantized version of [General Text Embeddings (GTE) model](https://huggingface.co/thenlper/gte-large) under MIT License. Used for all things RAG in the library.
+
+## emotion-bert-classifier.gguf
+
+A quantized version of [Emotions Analyzer](https://huggingface.co/logasanjeev/emotions-analyzer-bert) under MIT License, a fine-tuned BERT-base-uncased on GoEmotions for multi-label classification (28 emotions). Used for experimental sentiment analysis tasks. Optional.
+
+# What is Lethe AI Sharp?
+
+[Lethe AI Sharp](https://github.com/SerialKicked/Lethe-AI-Sharp/) is a modular, object‑oriented C# library that connects local or remote Large Language Model (LLM) backends to your applications (desktop tools, game engines, services). It also comes with its own light backend, allowing you to run a local LLM in the GGUF format directly without even having to rely on anything else.
 
 It unifies: chat personas, conversation/session management, streaming inference, long‑term memory, RAG (retrieval augmented generation), background agentic tasks, web search tools, TTS, and structured output generation. It is extensible, documented, and backend-agnostic (you write the same code no matter which backend is being used)
 
@@ -12,17 +28,13 @@ It unifies: chat personas, conversation/session management, streaming inference,
 
 **Self-Contained:** Built-in LlamaSharp backend means you can distribute a single executable that runs LLMs locally. No external server required, but external servers (KoboldAPI and OpenAI API) are supported too. 
 
+# Any program using Lethe AI Sharp?
 
-## Fixed ChatML Jinja Templates for Qwen 3.5
-
-This repo also contains fixed Jinja templates for Qwen 3.5 models. This one allows for system messages mid conversations (requirement for LetheAI) while removing an error that would trigger (at least) on LM Studio.
+Sure there's [Lethe AI Chat](https://github.com/SerialKicked/Lethe-AI-Chat/), it's a native Windows 10 frontend chat application. Compiled binaries are [available here](https://github.com/SerialKicked/Lethe-AI-Chat/releases).
 
-## gte-large.Q6_K.gguf
-
-A Q6_K quantized version of [General Text Embeddings (GTE) model](https://huggingface.co/thenlper/gte-large) under MIT License. Used for all things RAG in the library.
+![557083214-7a81b84c-4c64-4249-9dfc-e5e210213787](https://cdn-uploads.huggingface.co/production/uploads/63e80664e02ee67e8e570ec4/VqySILaszbL4LByQ7H106.png)
 
-## emotion-bert-classifier.gguf
+It's (at the very least) on par with other modern chat programs, and contains many unique features.
 
-A quantized version of [Emotions Analyzer](https://huggingface.co/logasanjeev/emotions-analyzer-bert) under MIT License, a fine-tuned BERT-base-uncased on GoEmotions for multi-label classification (28 emotions). Used for experimental sentiment analysis tasks.
 
 ---