# zjunlp/KnowLM

An Open-sourced Knowledgable Large Language Model Framework.

Repository: https://github.com/zjunlp/KnowLM
Canonical: https://ross.abutalabs.com/products/knowlm
Homepage: http://knowlm.zjukg.cn/
Language: Python
License: MIT
License Family: permissive
Topics: llama, large-language-models, pre-trained-language-models, language-model, instruction-following, deep-learning, chinese, english, instructions, models, reasoning, gpt-3, deepspeed, instruction-tuning, lora, pre-training, bilingual, pre-trained-model, knowlm, instructie
Last push: 2025-01-11T14:37:58+00:00

## Health v2 (maintenance only)
Score: 30/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 1, release rhythm 35, longevity 89
- inputs: {"age_days": 1250, "days_push": 599, "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 1386, forks 132 (observed 2026-08-28T04:04:35.024793+00:00)

## What it is
KnowLM is an open-source framework for building knowledgeable large language models, covering data processing, pre-training, fine-tuning, knowledge augmentation, and deployment. It also provides a model zoo with ready-to-use bilingual (Chinese/English) models such as ZhiXi, KnowLM-IE, OneKE, and OceanGPT.

## Use cases
- pretrain and fine-tune large language models on custom data
- instruction-tune a llama model with lora or deepspeed
- extract structured information from text with an LLM
- build a bilingual Chinese-English chat model
- augment LLM responses with retrieval-based knowledge
- detect hallucinations in LLM outputs
- edit knowledge inside a fine-tuned language model

## When to choose
- you need an end-to-end open-source pipeline for LLM pre-training and instruction tuning
- you want ready-made bilingual Chinese/English LLM checkpoints for information extraction
- you work in Python with GPU clusters and want DeepSpeed/LoRA support

## When to avoid
- you only need to call an LLM API without training or fine-tuning
- you lack GPU resources for large model training or inference
- you need a production-grade commercial LLM with vendor support

## Facets
- artifact type: framework
- maturity: active
- function: llm-training, machine-learning, rag, nlp, sdk
- domain: large-language-models, machine-learning, artificial-intelligence
- platform: python
- tags: llm, instruction-tuning, lora, deepspeed, bilingual, information-extraction, model-zoo, knowledge-editing, hallucination-detection, pre-training, natural-language-processing, gpu, linux

## Member repositories
- zjunlp/KnowLM (main) score 30

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:35.024793+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 2026-08-30T04:39:55.451930+00:00, confidence not recorded.
  - readme: https://github.com/zjunlp/KnowLM (fetched 2026-08-28T04:04:35.024793+00:00, sha a5a7f845b7dc)
- Data as of 2026-08-30T08:39:29.467469+00:00.