# replit/ReplitLM

Inference code and configs for the ReplitLM model family

Repository: https://github.com/replit/ReplitLM
Canonical: https://ross.abutalabs.com/products/replitlm
Homepage: https://huggingface.co/replit
Language: Python
License: Apache-2.0
License Family: permissive
Topics: ai, ai4code, llm
Archived: true
Last push: 2023-10-09T22:17:36+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 87
- inputs: {"age_days": 1223, "days_push": 1059, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1082, forks 143 (observed 2026-08-28T04:03:31.003762+00:00)

## What it is
Official repository with inference code, configs, and guides for the ReplitLM family of code-oriented language models, such as replit-code-v1-3b. It includes instructions for using the models with Hugging Face Transformers and for training or fine-tuning them with MosaicML's LLM Foundry and Composer.

## Use cases
- run replit-code-v1-3b for code completion locally
- fine-tune a replit code model on my own dataset
- do alpaca-style instruction tuning on replit-code models
- load replit lm checkpoints with hugging face transformers
- pretrain or continue training replit models with llm foundry
- try a hosted demo of a code llm

## When to choose
- you want to use or fine-tune the ReplitLM code models specifically
- you already use Hugging Face Transformers or MosaicML LLM Foundry
- you need Apache-2.0 licensed inference and training configs for these checkpoints

## When to avoid
- you need a general-purpose LLM not focused on code
- you want a actively developed model with frequent releases
- you need a hosted API rather than self-hosted model weights

## Facets
- artifact type: library
- maturity: maintenance
- function: llm-inference, llm-training, machine-learning
- domain: large-language-models, machine-learning, developer-tools
- platform: python, cross-platform
- tags: code-generation, hugging-face, model-checkpoints, fine-tuning, llm-foundry, instruct-tuning, gpu

## Member repositories
- replit/ReplitLM (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:31.003762+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 2026-08-30T06:51:17.641963+00:00, confidence not recorded.
  - readme: https://github.com/replit/ReplitLM (fetched 2026-08-28T04:03:31.003762+00:00, sha c397909f6b3c)
  - homepage: https://huggingface.co/replit (fetched 2026-08-29T12:53:48.733785+00:00, sha 7d96d0d43479)
  - site_page: https://huggingface.co/docs (fetched 2026-08-29T12:53:48.742712+00:00, sha bdec26667b98)
  - site_page: https://huggingface.co/docs/hub/organizations-cards (fetched 2026-08-29T12:53:48.746901+00:00, sha 635040b5f704)
  - site_page: https://huggingface.co/pricing (fetched 2026-08-29T12:53:48.744747+00:00, sha de6b7a178be5)
  - site_page: https://huggingface.co/huggingface (fetched 2026-08-29T12:53:48.748570+00:00, sha 048c056701fd)
- Data as of 2026-08-30T08:39:29.467469+00:00.