🦖 X—LLM: Cutting Edge & Easy LLM Finetuning

Interact with any LLM service

Simulate human behavior with mass LLMs

🦖 X—LLM: Simple & Cutting Edge LLM Finetuning

This repository features an example of how to utilize the xllm library. Included is a solution for a common type of assessment given to LLM engineers, who typically earn between $120,000 to $140,000 annually

Query LLM with Chain-of-Tought

A solution that could prioritize patients based on urgency, reducing wait times and ensuring those who need immediate care.

Conversation AI model for open domain dialogs

Jarvis-Chat is a Flask-based web application that utilizes various AI models to provide users with a conversational interface for answering questions and completing tasks. It features basic memory for follow-up questions, customizable system prompts, and allows you to select from a variety of AI models. Designed for ease of use,

Orion is a web-based chat interface that simplifies interactions with multiple AI model providers.

AI Accelerators-SC24-tutorial Repository

Using Cerebras LLM for Recursive Vector Disambiguation

This PWA offers a fully offline inference runtime with a chat model finetuned from Cerebras-GPT 111M

A simple tool to query LLMs from the terminal

Replicating a simple clone of NotebookLM using CrewAI + Cerebras (Llama3.1-70B) + ElevenLabs!

This evaluation explores the In-context learning (ICL) capabilities of pre-trained language models on arithmetic tasks and sentiment analysis using synthetic datasets. The goal is to use different prompting strategies—zero-shot, few-shot, and chain-of-thought—to assess the performance of these models on the given tasks.