Yi 6B

🚀 Yi

The Yi series is a next - generation open - source large language model developed from scratch. It offers high - performance chat and base models, excelling in both English and Chinese on various benchmarks. With a unique training approach, Yi provides a powerful and reliable solution for a wide range of language - related tasks.

🚀 Quick Start

Choose your path

There are multiple ways to start using Yi, including pip, docker, llama.cpp, conda - lock, and a web demo.

Quick start - pip

You can install Yi using pip to quickly get started with the model.

Quick start - docker

Using Docker allows for easy deployment and management of the Yi environment.

Quick start - llama.cpp

llama.cpp provides an alternative way to run Yi models with specific optimizations.

Quick start - conda - lock

conda - lock can be used to ensure reproducible environments for Yi.

Web demo

You can try Yi interactively through the web demo.

✨ Features

Introduction

• 🤖 The Yi series models are the next generation of open - source large language models trained from scratch by 01.AI.
• 🙌 Targeted as a bilingual language model and trained on 3T multilingual corpus, the Yi series models become one of the strongest LLMs worldwide, showing promise in language understanding, commonsense reasoning, reading comprehension, and more. For example:
  • The Yi - 34B - Chat model landed in second place (following GPT - 4 Turbo), outperforming other LLMs (such as GPT - 4, Mixtral, Claude) on the AlpacaEval Leaderboard (based on data available up to January 2024).
  • The Yi - 34B model ranked first among all existing open - source models (such as Falcon - 180B, Llama - 70B, Claude) in both English and Chinese on various benchmarks, including Hugging Face Open LLM Leaderboard (pre - trained) and C - Eval (based on data available up to November 2023).
  • 🙏 (Credits to Llama) Thanks to the Transformer and Llama open - source communities, as they reduce the efforts required to build from scratch and enable the utilization of the same tools within the AI ecosystem.

News

• 🔥 2024 - 07 - 29: The Yi Cookbook 1.0 is released, featuring tutorials and examples in both Chinese and English.
• 🎯 2024 - 05 - 13: The [Yi - 1.5 series models](https://github.com/01 - ai/Yi - 1.5) are open - sourced, further improving coding, math, reasoning, and instruction - following abilities.
• 🎯 2024 - 03 - 16: The Yi - 9B - 200K is open - sourced and available to the public.
• 🎯 2024 - 03 - 08: Yi Tech Report is published!
• 🔔 2024 - 03 - 07: The long text capability of the Yi - 34B - 200K has been enhanced. In the "Needle - in - a - Haystack" test, the Yi - 34B - 200K's performance is improved by 10.5%, rising from 89.3% to an impressive 99.8%. We continue to pre - train the model on 5B tokens long - context data mixture and demonstrate a near - all - green performance.
• 🎯 2024 - 03 - 06: The Yi - 9B is open - sourced and available to the public. Yi - 9B stands out as the top performer among a range of similar - sized open - source models (including Mistral - 7B, SOLAR - 10.7B, Gemma - 7B, DeepSeek - Coder - 7B - Base - v1.5 and more), particularly excelling in code, math, common - sense reasoning, and reading comprehension.
• 🎯 2024 - 01 - 23: The Yi - VL models, [Yi - VL - 34B](https://huggingface.co/01 - ai/Yi - VL - 34B) and [Yi - VL - 6B](https://huggingface.co/01 - ai/Yi - VL - 6B), are open - sourced and available to the public. [Yi - VL - 34B](https://huggingface.co/01 - ai/Yi - VL - 34B) has ranked first among all existing open - source models in the latest benchmarks, including MMMU and CMMMU (based on data available up to January 2024).
• 🎯 2023 - 11 - 23: [Chat models](https://github.com/01 - ai/Yi#chat - models) are open - sourced and available to the public. This release contains two chat models based on previously released base models, two 8 - bit models quantized by GPTQ, and two 4 - bit models quantized by AWQ.
  • Yi - 34B - Chat
  • Yi - 34B - Chat - 4bits
  • Yi - 34B - Chat - 8bits
  • Yi - 6B - Chat
  • Yi - 6B - Chat - 4bits
  • Yi - 6B - Chat - 8bits You can try some of them interactively at:
    • [Hugging Face](https://huggingface.co/spaces/01 - ai/Yi - 34B - Chat)
    • [Replicate](https://replicate.com/01 - ai)
• 🔔 2023 - 11 - 23: The Yi Series Models Community License Agreement is updated to [v2.1](https://github.com/01 - ai/Yi/blob/main/MODEL_LICENSE_AGREEMENT.txt).
• 🔥 2023 - 11 - 08: Invited test of Yi - 34B chat model.
  • Application form:
    • English
    • Chinese
• 🎯 2023 - 11 - 05: [The base models](https://github.com/01 - ai/Yi#base - models), Yi - 6B - 200K and Yi - 34B - 200K, are open - sourced and available to the public. This release contains two base models with the same parameter sizes as the previous release, except that the context window is extended to 200K.
• 🎯 2023 - 11 - 02: [The base models](https://github.com/01 - ai/Yi#base - models), Yi - 6B and Yi - 34B, are open - sourced and available to the public. The first public release contains two bilingual (English/Chinese) base models with the parameter sizes of 6B and 34B. Both of them are trained with 4K sequence length and can be extended to 32K during inference time.

Models

Chat models

Base models

The base models of Yi provide a solid foundation for further fine - tuning and development.

Model info

The Yi models have detailed information about their architecture, training data, and performance.

How to use Yi?

Fine - tuning

You can fine - tune Yi models to adapt them to specific tasks and domains.

Quantization

Quantization techniques can be applied to optimize the performance and memory usage of Yi models.

Deployment

Make sure you meet the software and hardware requirements when deploying Yi models.

FAQ

Check the frequently asked questions section for common issues and solutions.

Learning hub

Grow at [Yi Learning Hub](#learning - hub) to get more knowledge about Yi.

Why Yi?

Ecosystem

Upstream

The upstream of the Yi ecosystem provides the necessary support and resources for model development.

Downstream

Serving

Efficient serving solutions are available for deploying Yi models.

Quantization

Advanced quantization methods are integrated into the ecosystem.

Fine - tuning

The ecosystem supports fine - tuning of Yi models for various applications.

API

APIs are provided to facilitate the use of Yi models in different projects.

Benchmarks

Base model performance

The base models of Yi show excellent performance on multiple benchmarks.

Chat model performance

The chat models of Yi also perform well in relevant evaluations.

Tech report

Citation

You can cite the Yi Tech Report for academic and research purposes.

Who can use Yi?

Yi is suitable for a wide range of users, including researchers, developers, and enterprises.

📄 License

The Yi series models are released under the Apache - 2.0 license.