# imoneoi/openchat

OpenChat: Advancing Open-source Language Models with Imperfect Data

Repository: https://github.com/imoneoi/openchat
Canonical: https://ross.abutalabs.com/products/openchat
Homepage: https://openchat.team
Language: Python
License: Apache-2.0
License Family: permissive
Topics: large-language-models, open-source, transformers
Last push: 2024-09-13T07:46:22+00:00

## Health v2 (maintenance only)
Score: 20/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 85
- inputs: {"age_days": 1196, "days_push": 719, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5490, forks 430 (observed 2026-08-28T04:09:19.812680+00:00)

## What it is
OpenChat is a library of open-source large language models fine-tuned with C-RLFT, an offline reinforcement learning strategy that learns from mixed-quality data without preference labels. It includes training and evaluation code plus model weights (e.g., OpenChat 3.6 based on Llama 3) that run on consumer GPUs.

## Use cases
- fine-tune an open-source chat llm on mixed-quality data
- run a 7b chatgpt-quality model on a consumer gpu
- reproduce llm benchmark evaluations like gpt4 correct
- train a chat model without preference labels
- download openchat model weights for local inference

## When to choose
- you want high-performing open chat models with permissive Apache-2.0 licensing
- you need to train or evaluate chat llms using the C-RLFT method
- you have limited GPU resources but need strong conversational performance

## When to avoid
- you need a hosted chat API rather than self-hosted model weights
- you require the latest actively developed LLM training framework
- you need multimodal or non-chat model capabilities

## Facets
- artifact type: library
- maturity: maintenance
- function: llm-training, machine-learning, llm-inference
- domain: large-language-models, deep-learning, artificial-intelligence
- platform: python
- tags: open-source-llm, c-rlft, fine-tuning, chat-models, reinforcement-learning, gpu, linux

## Member repositories
- imoneoi/openchat (main) score 20

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:19.812680+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 2026-08-29T17:56:21.248657+00:00, confidence not recorded.
  - readme: https://github.com/imoneoi/openchat (fetched 2026-08-28T04:09:19.812680+00:00, sha dbd0769e9fed)
- Data as of 2026-08-30T08:39:29.467469+00:00.