# TigerResearch/TigerBot

TigerBot: A multi-language multi-task LLM

Repository: https://github.com/TigerResearch/TigerBot
Canonical: https://ross.abutalabs.com/products/tigerbot
Homepage: https://www.tigerbot.com
Language: Python
License: Apache-2.0
License Family: permissive
Topics: llm, nlp, chinese, data, llama2
Last push: 2024-12-28T06:07:56+00:00

## Health v2 (maintenance only)
Score: 29/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 86
- inputs: {"age_days": 1209, "days_push": 613, "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 2259, forks 188 (observed 2026-08-28T04:06:31.651372+00:00)

## What it is
TigerBot is a multi-language, multi-task large language model project from TigerResearch, providing pretrained and chat-tuned model weights (up to 70B with 100K context), training/fine-tuning code, and Chinese-focused datasets. It also ships domain extensions such as a Chinese clinical terminology system (MedCT) and medical NER models.

## Use cases
- train or fine-tune a Chinese large language model
- download an open-source Chinese chat LLM for self-hosting
- run a multilingual LLM with long 100K context
- build Chinese medical NER with clinical terminology data
- deploy a GPT-style chatbot on my own GPU server
- get high-quality Chinese instruction tuning datasets

## When to choose
- you need strong Chinese-language LLM performance or Chinese training data
- you want open Apache-2.0 model weights you can self-host and fine-tune
- you need long-context chat models or medical-domain NLP resources

## When to avoid
- you only need a hosted API without managing GPUs
- you need the newest frontier open models rather than a Chinese-focused family
- your project is English-only with no Chinese requirements

## Facets
- artifact type: library
- maturity: maintenance
- function: llm-training, llm-inference, nlp, machine-learning, rag
- domain: large-language-models, artificial-intelligence
- platform: python
- tags: chinese-llm, multilingual, llama2, fine-tuning, medical-nlp, huggingface, model-weights, natural-language-processing, chinese-nlp, gpu, linux

## Member repositories
- TigerResearch/TigerBot (main) score 29

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:31.651372+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 2026-08-30T02:42:40.255113+00:00, confidence not recorded.
  - readme: https://github.com/TigerResearch/TigerBot (fetched 2026-08-28T04:06:31.651372+00:00, sha 3bebc5398d18)
- Data as of 2026-08-30T08:39:29.467469+00:00.