Open Source C++ Large Language Models (LLM)

Inference of LLaMA model in pure C/C++

Run a fast ChatGPT-like model locally on your device. This combines the LLaMA foundation model with an open reproduction of Stanford Alpaca a fine-tuning of the base model to obey instructions (akin to the RLHF used to train ChatGPT) and a set of modifications to llama.cpp to add a chat interface. Download the zip file corresponding to your operating system from the latest release. The weights are based on the published fine-tunes from alpaca-lora, converted back into a PyTorch checkpoint with a modified script and then quantized with llama.cpp the regular way.

llamafile lets you distribute and run LLMs with a single file. (announcement blog post). Our goal is to make open LLMs much more accessible to both developers and end users. We're doing that by combining llama.cpp with Cosmopolitan Libc into one framework that collapses all the complexity of LLMs down to a single-file executable (called a "llamafile") that runs locally on most computers, with no installation. The easiest way to try it for yourself is to download our example llamafile for the LLaVA model (license: LLaMA 2, OpenAI). LLaVA is a new LLM that can do more than just chat; you can also upload images and ask it questions about them. With llamafile, this all happens locally; no data ever leaves your computer.

DomE Experiment is an implementation of a reference architecture for creating information systems from the automated evolution of the domain model. The architecture comprises elements that guarantee user access through automatically generated interfaces for various devices, integration with external information sources, data and operations security, automatic generation of analytical information, and automatic control of business processes. All these features are generated from the domain model, which is, in turn, continuously evolved from interactions with the user or autonomously by the system itself. Thus, an alternative to the traditional software production processes is proposed, which involves several stages and different actors, sometimes demanding a lot of time and money without obtaining the expected result. With software engineering techniques, self-adaptive systems, and artificial intelligence, it is possible, the integration between design time and execution time.

Besides the usual FP32, it supports FP16, quantized INT4, INT5 and INT8 inference. This project is focused on CPU, but cuBLAS is also supported. RWKV is a novel large language model architecture, with the largest model in the family having 14B parameters. In contrast to Transformer with O(n^2) attention, RWKV requires only state from the previous step to calculate logits. This makes RWKV very CPU-friendly on large context lengths.