Ambrosia helps you clean up your LLM datasets using other LLMs.
Directory
Search results
Published directory entries matching your search.
An overview of the current attack techniques on LLMs by Marcello Carboni.
7B Large Language Model fine-tune by 34B Chinese Character Corpus, based on LLaMA and Alpaca.
Official inference framework for 1-bit LLMs, by Microsoft. opensource.
Accessible large language models via k-bit quantization for PyTorch.
Creates, rewrites or summarizes written content with language models.
BigScience Large Open-science Open-access Multilingual Language Model.
BrainSoup supports AI agents, automated workflows, orchestration, or delegated tasks.
"Tips and tricks for working with Large Language Models like OpenAI's GPT-4".
Role-playing approach for LLMs and auto-agents like BabyAGI & AutoGPT.
Interactive Hugging Face app that shares a machine-learning model, framework, demonstration or technical resource.
Project that automatically maps relationship networks by parsing public data using LLMs and visualizes it as an interactive graph.
Cohere provides access to advanced Large Language Models and NLP tools.
A curated list of language modeling researches for code and related datasets.
Open Code LLMs for Code Understanding and Generation.
Cohere provides access to advanced Large Language Models and NLP tools.
A8e70ca5a9942e399a04543b16dff92c65bd6a94b4a8fe97253e51bfff480743.
Teaching LLMs memory management for unbounded context [[demo page]](https://memgpt.ai/) [[arxiv]](https://arxiv.org/abs/2310.08560).
Curate and annotate vision, audio, and LLM datasets, track experiments, and manage models on a single platform.
Track real-time GPU and LLM pricing across all cloud and inference providers.
. Practical AI engineering and generative AI explained simply: RAG, agents, and LLM application patterns for builders.
Dominodatalab supports deploying, serving, monitoring, or operating AI and machine-learning systems.
LLM Agent, GenAI Agent, AI Service, Framework, Python, Chatbots, RAG, Agentic Framework.
Talk by Princeton professor Arvind Narayanan.