Lethe AI Sharp
This repo contains useful content for the 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)
No Python Dependencies: Pure .NET 10 C# implementation. No Python runtime, no conda environments, no pip hell.
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.
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.
gte-large.Q6_K.gguf
A Q6_K quantized version of General Text Embeddings (GTE) model under MIT License. Used for all things RAG in the library.
emotion-bert-classifier.gguf
A quantized version of Emotions Analyzer under MIT License, a fine-tuned BERT-base-uncased on GoEmotions for multi-label classification (28 emotions). Used for experimental sentiment analysis tasks.
- Downloads last month
- 35
6-bit