# 01-ai/Yi

A series of large language models trained from scratch by developers @01-ai

Repository: https://github.com/01-ai/Yi
Canonical: https://ross.abutalabs.com/products/yi
Homepage: https://01.ai
Language: Jupyter Notebook
License: Apache-2.0
License Family: permissive
Topics: large-language-models
Last push: 2024-11-27T09:25:57+00:00

## Health v2 (maintenance only)
Score: 27/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 73
- inputs: {"age_days": 1034, "days_push": 644, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 7836, forks 498 (observed 2026-08-28T04:10:05.911781+00:00)

## What it is
Yi is a family of open-source large language models trained from scratch by 01.AI, including base and chat models in multiple sizes, with bilingual (English/Chinese) capabilities. The repository provides model weights, quick-start guides for pip, Docker, and llama.cpp, plus fine-tuning, quantization, and deployment resources.

## Use cases
- run an open-source bilingual LLM locally
- fine-tune a large language model on my own data
- quantize an LLM for cheaper inference
- self-host a chat model with llama.cpp
- compare open LLM benchmarks before choosing a base model
- deploy an LLM behind an API

## When to choose
- you need an Apache-2.0 licensed LLM you can self-host and fine-tune
- your application needs strong English-Chinese bilingual performance
- you want a base model to build a chat assistant or RAG pipeline on

## When to avoid
- you need a managed hosted API without running your own infrastructure
- you need frontier-level reasoning beyond what mid-size open models offer
- you need multimodal (image/audio) input from the base model family

## Facets
- artifact type: library
- maturity: maintenance
- function: llm-inference, llm-training, machine-learning, deep-learning
- domain: large-language-models, deep-learning, artificial-intelligence
- platform: python, cross-platform
- tags: open-source-llm, bilingual-models, foundation-models, fine-tuning, quantization, chat-models, hugging-face, natural-language-processing, gpu, docker

## Member repositories
- 01-ai/Yi (main) score 27

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:05.911781+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:33:58.598790+00:00, confidence not recorded.
  - readme: https://github.com/01-ai/Yi (fetched 2026-08-28T04:10:05.911781+00:00, sha 1a9081d0f4c6)
  - homepage: https://01.ai (fetched 2026-08-29T08:30:34.640551+00:00, sha ccadaac4ba2e)
  - site_page: https://www.01.ai/about.html (fetched 2026-08-29T08:30:34.643448+00:00, sha 717550aeff43)
- Data as of 2026-08-30T08:39:29.467469+00:00.