Update README.md

README.md

@@ -4,7 +4,7 @@ license: mit
 
 # Lethe AI Sharp
 
-Misc 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. 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.
 
 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)
 
@@ -17,15 +17,12 @@ It unifies: chat personas, conversation/session management, streaming inference,
 
 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.
 
-
-Two models required by the [**Lethe-AI C# Middleware Library**](https://github.com/SerialKicked/Lethe-AI-Sharp)
-
 ## 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 sentiment analysis tasks.
+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.
 
 ---