# FreedomIntelligence/LLMZoo

⚡LLM Zoo is a project that provides data, models, and evaluation benchmark for large language models.⚡

Repository: https://github.com/FreedomIntelligence/LLMZoo
Canonical: https://ross.abutalabs.com/products/llmzoo
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2023-11-26T17:48:30+00:00

## Health v2 (maintenance only)
Score: 30/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 89
- inputs: {"age_days": 1250, "days_push": 1011, "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 2935, forks 194 (observed 2026-08-28T04:07:30.829052+00:00)

## What it is
LLM Zoo is a project providing data, models, and evaluation benchmarks for large language models, including the multilingual Phoenix and Chimera instruction-following models. It includes training code, CLI inference, and web deployment tools to help users replicate and run ChatGPT-like LLMs.

## Use cases
- train a multilingual instruction-following LLM
- run a chat model from the command line
- evaluate and compare open-source LLMs
- download instruction-tuned model weights
- deploy a chatbot web application
- get multilingual instruction tuning data

## When to choose
- you want to replicate or fine-tune an open ChatGPT-like model
- you need multilingual instruction-following data or models
- you want a benchmark comparing open LLMs like MOSS and Phoenix

## When to avoid
- you need a production-grade, actively maintained LLM framework
- you only want to use commercial APIs like OpenAI
- you need the latest model architectures, as the project's last release was late 2023

## Facets
- artifact type: framework
- maturity: maintenance
- function: llm-training, machine-learning, llm-inference, chatbot, cli
- domain: large-language-models, artificial-intelligence, machine-learning
- platform: python, cli, cross-platform
- tags: instruction-tuning, open-source-llm, multilingual, evaluation-benchmark, chatgpt-alternative, huggingface, natural-language-processing

## Member repositories
- FreedomIntelligence/LLMZoo (main) score 30

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:30.829052+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 2026-08-30T07:33:10.043773+00:00, confidence not recorded.
  - readme: https://github.com/FreedomIntelligence/LLMZoo (fetched 2026-08-28T04:07:30.829052+00:00, sha b66857b7cf26)
- Data as of 2026-08-30T08:39:29.467469+00:00.