Directory
Published directory entries matching your search.
Annotated talk slides by Arvind Narayanan and Sayash Kapoor of Princeton University, dated October 4, 2023, on evaluating large language models. The slides discuss three hard problems in LLM evaluation: prompt sensitivity, construct validity and contamination, and examine questions about ChatGPT's behavior over time and its political bias.
Falcon LLM is described as a generative large language model that supports applications and use cases. The site presents models in the Falcon LLM family, including Falcon-H1 and Falcon-E, and lists Falcon-H1 model insights. It also references Falcon Arabic for Modern Standard Arabic and dialects, and names Falcon-Emirati, Falcon-ASR and Falcon-OCR-Arabic.
FastChat is an open platform for training, serving, and evaluating large language model based chatbots. Its core features include training and evaluation code for models such as Vicuna and MT-Bench, and a distributed multi-model serving system with a web UI and OpenAI-compatible RESTful APIs.
Documentation for Fine Tuning Guide, covering setup, features, and practical usage.
FlexGen is a software project that enables running large language models on a single GPU. It focuses on throughput-oriented scenarios, offering an approach to efficient inference. The project is available on GitHub as FMInference/FlexLLMGen.
Flux is a machine learning library built as a pure-Julia stack, offering lightweight abstractions over Julia's native GPU and automatic differentiation support. It is compiled and eager, and existing Julia libraries can be incorporated into Flux models. Its ecosystem includes probabilistic programming, graph neural networks, computer vision and natural language processing packages, and it is maintained by a community team.
FutureTools is a curated AI news and tools site by Matt Wolfe. It aggregates AI headlines, expert commentary, top tools, and interviews, and offers a newsletter described as having 250,000+ subscribers.
Creates, rewrites or summarizes written content with language models.
Creates, rewrites or summarizes written content with language models.
The article 'Generative AI: A Creative New World' by Sequoia Capital discusses the emergence of a powerful new class of large language models that enable machines to write, code, draw, and create with credible or superhuman results. It contrasts analytical AI with creative AI.
Genmo is a research lab that develops open models for video generation. Its Mochi 1 model is an open-source text-to-video model, available through an open-source repository or ComfyUI and an interactive playground. The playground creates AI-generated videos, and FAQ materials describe MP4 output, text-to-video generation, and Free, Lite, Standard, and Pro plans.
Google tool for building, testing, and experimenting with Gemini prompts, models, and API workflows.
Google tool for building, testing, and experimenting with Gemini prompts, models, and API workflows.
This is a Kaggle page for a Google prompt engineering whitepaper. It invites users to join a community of builders, researchers and labs evaluating AI agents, models and frontier technology through crowdsourced benchmarks, competitions and hackathons.
BIG-bench is a collaborative benchmark intended to probe large language models and extrapolate their future capabilities. It includes more than 200 tasks, summarized by keyword and task name. The repository was archived by its owner and is now read-only.
GPT Mobile is an Android chat application that supports responses from multiple large language models simultaneously. It is a bring-your-own-API-key client that supports OpenAI, Anthropic, Google, and Ollama, and is built with Material3 and Compose.
GPT4All is a private, local AI chatbot tool developed by Nomic. It enables users to run open-source AI models directly on their personal devices without cloud connectivity, with all user data remaining on the local machine.
PandasAI is an open-source library that enables conversational data analysis using large language models and retrieval-augmented generation. It allows users to interact with databases or datalakes supporting SQL, CSV, and parquet file formats.
A Hacker News discussion thread about the ChemCrow preprint on augmenting large-language models with chemistry tools. Commenters raise citation problems and question how a program can make an already widely used medicine less toxic.
HF Learn supports machine learning models, deployment, inspection, datasets, or AI development workflows.
Creates, rewrites or summarizes written content with language models.
Hume provides voice AI evaluation infrastructure through its VoiceEQ platform. It turns real-world use cases into targeted evaluation suites and combines automated measurement with human judgment to diagnose failures in voice models and agents. The platform covers TTS, speech-to-speech, ASR, and cascaded systems, and the company reports support for over 50 languages.
A first-person essay by former writing and literature teacher Victoria Livingstone describing why she left teaching, citing students' reliance on large language models such as ChatGPT for drafting and revising written work. The piece discusses pedagogical attempts to address AI use and the difficulty of evaluating AI-revised text.
Illusion Diffusion is a Hugging Face Space developed by AP123 for AI image generation. Users can upload an image to use as an illusion pattern, input a text prompt describing their desired output, and the app generates high-quality artwork that blends the uploaded pattern with the prompt content.
