# nlpxucan/WizardLM

LLMs build upon Evol Insturct: WizardLM, WizardCoder, WizardMath

Repository: https://github.com/nlpxucan/WizardLM
Canonical: https://ross.abutalabs.com/products/wizardlm
Language: Python
License Family: other
Last push: 2025-06-07T01:35:05+00:00

## Health v2 (maintenance only)
Score: 31/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 25, release rhythm 8, longevity 87
- inputs: {"age_days": 1228, "days_push": 453, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 9483, forks 745 (observed 2026-08-28T04:10:31.354960+00:00)

## What it is
The WizardLM family of instruction-tuned large language models (WizardLM, WizardCoder, WizardMath) built with the Evol-Instruct data evolution technique, including training code and released model weights. It is primarily a research/model release repository rather than a reusable software library.

## Use cases
- fine-tune an LLM to follow complex instructions
- download an open-source code generation model
- improve math reasoning of a language model
- generate evolved instruction data for LLM training
- run an open-source ChatGPT alternative locally

## When to choose
- you want to study or reproduce Evol-Instruct instruction tuning
- you need open model weights for coding or math tasks
- you are benchmarking open LLMs against ChatGPT-class models

## When to avoid
- you need a production inference server or chat API out of the box
- you need a permissively licensed codebase - the repo has no explicit license file
- you want actively maintained tooling rather than research artifacts

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: llm-training, machine-learning, prompt-engineering
- domain: large-language-models, machine-learning, deep-learning, artificial-intelligence
- platform: python
- tags: instruction-tuning, evol-instruct, fine-tuning, wizardcoder, wizardmath, open-source-llm, model-weights, gpu, linux

## Member repositories
- nlpxucan/WizardLM (main) score 31

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:31.354960+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 2026-08-29T17:22:03.360142+00:00, confidence not recorded.
  - readme: https://github.com/nlpxucan/WizardLM (fetched 2026-08-28T04:10:31.354960+00:00, sha d563a873cbdc)
- Data as of 2026-08-30T08:39:29.467469+00:00.