# aixcoder-plugin/aiXcoder-7B

official repository of aiXcoder-7B Code Large Language Model

Repository: https://github.com/aixcoder-plugin/aiXcoder-7B
Canonical: https://ross.abutalabs.com/products/aixcoder-7b
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2025-07-09T09:13:50+00:00

## Health v2 (maintenance only)
Score: 29/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 30, release rhythm 8, longevity 63
- inputs: {"age_days": 886, "days_push": 420, "days_rel": 420, "gap_med": null, "n_releases_24m": 1}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2271, forks 360 (observed 2026-08-28T04:06:33.145045+00:00)

## What it is
Official repository for aiXcoder-7B, an open-weights 7B-parameter code large language model trained on 1.2T tokens for code completion, generation, and comprehension across multiple programming languages. It includes inference examples, quantization support, fine-tuning scripts, and companion IDE plugins for VS Code and JetBrains.

## Use cases
- run a local code completion llm
- generate code from natural language descriptions
- fine-tune a code llm on my own codebase
- self-host a code model for ide autocompletion
- evaluate code llms on nl2code benchmarks
- quantize a 7b model to run on limited gpu memory

## When to choose
- you need an open-weights code llm you can self-host and fine-tune
- you want strong fill-in-the-middle code completion at 7B scale
- you want a model with ready-made VS Code or JetBrains integration

## When to avoid
- you need a general-purpose chat or reasoning assistant rather than a code model
- you have no GPU and cannot run a 7B model even quantized
- you only want a hosted API without managing model weights

## Facets
- artifact type: library
- maturity: active
- function: llm-inference, llm-training, machine-learning
- domain: large-language-models, developer-tools, deep-learning
- platform: python
- tags: code-generation, code-completion, open-weights, fill-in-the-middle, nl2code, gpu, docker

## Member repositories
- aixcoder-plugin/aiXcoder-7B (main) score 29

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:33.145045+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 2026-08-30T02:41:47.733584+00:00, confidence not recorded.
  - readme: https://github.com/aixcoder-plugin/aiXcoder-7B (fetched 2026-08-28T04:06:33.145045+00:00, sha 7f9be39468a1)
- Data as of 2026-08-30T08:39:29.467469+00:00.