# linyiLYi/bilibot

A local chatbot fine-tuned by bilibili user comments.

Repository: https://github.com/linyiLYi/bilibot
Canonical: https://ross.abutalabs.com/products/bilibot
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2024-05-15T15:01:13+00:00

## Health v2 (maintenance only)
Score: 24/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 60
- inputs: {"age_days": 849, "days_push": 840, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3139, forks 369 (observed 2026-08-28T04:07:45.794048+00:00)

## What it is
A local chatbot fine-tuned from Bilibili user comments, built on Qwen1.5-32B-Chat using Apple's MLX LoRA fine-tuning. It supports text chat and generates spoken Q&A dialogues via GPT-SoVITS voice models.

## Use cases
- run a local chatbot fine-tuned on bilibili comments
- fine-tune qwen with lora on apple silicon using mlx
- generate voice dialogue from text questions
- quantize a large language model for faster local inference
- clone voices with gpt-sovits for a chatbot

## When to choose
- you want a locally running Chinese chatbot with a playful bilibili-style persona
- you're on macOS with Apple Silicon and want an MLX LoRA fine-tuning example
- you need text chat plus TTS voice responses in one project

## When to avoid
- you need a production-grade or multi-user chatbot service
- you don't have Apple Silicon hardware or sufficient memory for a 32B model
- you need English-language conversation or up-to-date knowledge

## Facets
- artifact type: application
- maturity: maintenance
- function: llm-training, llm-inference, tts, chatbot
- domain: large-language-models, machine-learning, speech-processing, chatbots
- platform: python
- tags: fine-tuning, lora, mlx, qwen, gpt-sovits, bilibili, voice-cloning, local-llm, macos, gpu

## Member repositories
- linyiLYi/bilibot (main) score 24

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:45.794048+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 2026-08-30T07:26:03.231813+00:00, confidence not recorded.
  - readme: https://github.com/linyiLYi/bilibot (fetched 2026-08-28T04:07:45.794048+00:00, sha 0c8e7c1c46c0)
- Data as of 2026-08-30T08:39:29.467469+00:00.