Open-Source LLM models

June 2023

# mpt-30b-instruct MPT-30B-Instruct is a model for short-form instruction following.

June 2023

MPT-30B is an open source text model with an 8k token context window and efficient inference and training via FlashAttention, making it easy to deploy on a single GPU.

June 2023

StarCoder Plus is an open source 15.5B parameter Language Model trained on English and over 80 programming languages, capable of handling code.

June 2023

wizardcoder-15b-1.0 is an open-source language model capable of generating code, with a release date of 16/06/2023.

May 2023

30b-lazarus is an open source text model that will be released on May 25, 2023, with a demo available at the access link provided.

May 2023

StarCoder is an open source Large Language Model for Code trained on permissively licensed data from GitHub, including from 80+ programming languages, Git commits, GitHub issues, and Jupyter notebooks.

May 2023

This document includes information about the codet5p open source text model developed by Salesforce.

April 2023

StableLM-Tuned-Alpha is an open-source 7B parameter decoder-only language model suite fine-tuned for chat and instruction-following tasks.

April 2023

Dolly V2 is an open source, instruction-following large language model trained on ~15k fine-tuning records generated by Databricks employees.

April 2023

Pythia-12b is an open-source text model with a size of 12B, trained on a diverse 825GiB dataset of English texts.

April 2023

This is a document describing a software project called "camel-5b-hf". It is an open source text project with an access link to huggingface.co. The release date is set for January 4th, 2023, and there is a demo link available at chatcamel.vercel.app. The project is not deprecated.

February 2023

Palmyra Base is an open source, text-based language model primarily pre-trained with English text and utilizing a causal language modeling (CLM) objective.

December 2022

OPT-IML is an open source text type model that is optimized using instruction-tuned versions of OPT and trained on OPT-IML Bench, a large benchmark for Instruction MetaLearning (IML) of 2000 NLP tasks. It has a size of 175B, released on 22/12/2022 and is licensed under the Open Source license.

October 2022

Flan T5 XXL is an open-source, high-performance text model with 11B parameters, achieving state-of-the-art performance on many benchmarks, and fine-tuned on over 1000 additional tasks covering more languages.

October 2022

This document appears to be a template or metadata file for an open source project called "ul-2," with release information and links to announcements.

August 2022

This document contains information about glm-130b, an open source text type tool with release date of 04/08/2022. It is not currently deprecated and has an announcement link and demo link.

June 2022

This document describes the CodeGeex project, an open source project that provides access to multilingual code. It includes capabilities for code and a demo link.

February 2020

This document describes a software project called t5, which is open source and consists of text. It was released on 24/02/2020 and is not deprecated.

November 2019

LaBSE is an open source, multilingual embedding model capable of producing high-quality sentence embeddings for a wide range of applications.

This document appears to be related to a software project called "chatglm-6b". It includes information about the license, type, capabilities, and other technical details of the project, but a very short description of the project's purpose or function is not provided.

Falcon 40B Instruct is an open-source, 40B parameters, multilingual causal decoder-only model with instruct capabilities.

Falcon is a multilingual decoder-only model for text-related tasks.

YaLM 100B is a powerful open-source text-generation neural network.

This document provides information about the codegen project and its capabilities.

GPT NeoXT Chat Base (20B) is an open-source text model fine-tuned from GPT-NeoX for developing chatbots.

gpt-jt is an open source text generation model that can be used for various natural language processing tasks.

OPT (Open Pre-trained Transformers) is an open-source suite of decoder-only transformers with 175B parameters, designed to support responsible research and development.

GPT-NeoX is an open source text model.

gpt-j is an open source text model.

Bloomz is an open source multilingual text model with capabilities for various natural language processing tasks.

This is a text-based, multilingual open source model called Bloom, which can be accessed through the provided link.

SantaCoder is an Open Source text-based model trained on a 1.1B parameter dataset of Python, Java, and JavaScript code, supporting code capabilities and coming with a demo link.

GPT Neo is an open source text model implementation with a range of capabilities for natural language processing.

Alpaca 7B is an open source text model for instruction-following, based on the LLaMA 7B model and fine-tuned on 52K demonstrations.