# meta-llama/codellama

Inference code for CodeLlama models

Repository: https://github.com/meta-llama/codellama
Canonical: https://ross.abutalabs.com/products/codellama
Language: Python
License: NOASSERTION
License Family: other
Archived: true
Last push: 2024-08-12T12:49:54+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 78
- inputs: {"age_days": 1105, "days_push": 751, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, archived, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 16265, forks 1939 (observed 2026-08-28T04:11:15.015565+00:00)

## What it is
Official Meta repository with inference code for the Code Llama family of large language models for code, based on Llama 2. It provides minimal example code to load and run the pretrained and instruction-tuned models (7B-34B parameters).

## Use cases
- generate code with a local LLM
- run Code Llama inference locally
- download and load Code Llama model weights
- infill code in the middle of a file
- follow natural language instructions to write code
- specialized Python code generation

## When to choose
- you want to run the official Code Llama models with Meta's reference code
- you need infilling or long-context code generation with Code Llama
- you want to experiment with open code LLM weights

## When to avoid
- you want a production-ready serving stack rather than minimal example code
- you need a permissively licensed model for commercial redistribution without restrictions
- you prefer using optimized inference engines like vLLM or llama.cpp

## Facets
- artifact type: library
- maturity: maintenance
- function: llm-inference, machine-learning
- domain: large-language-models, artificial-intelligence, developer-tools
- platform: python
- tags: code-generation, llama, meta, model-weights, inference-code, gpu, linux

## Member repositories
- meta-llama/codellama (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:15.015565+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 2026-08-29T17:05:09.816692+00:00, confidence not recorded.
  - readme: https://github.com/meta-llama/codellama (fetched 2026-08-28T04:11:15.015565+00:00, sha 13b2e4ad916a)
- Data as of 2026-08-30T08:39:29.467469+00:00.