bilibot

A local chatbot trained by fine-tuning Bilibili user comments

CommonProductchattingChatbotLocal Deployment

bilibot is a local chatbot trained on Bilibili user comments, supporting both text chat and voice dialogue. It uses Qwen1.5-32B-Chat as the base model and is further fine-tuned with Apple's mlx-lm LORA project. The voice generation part is based on the GPT-SoVITS project, utilizing the Paimon voice model. This chatbot can quickly generate conversational content and is suitable for scenarios requiring intelligent dialogue systems.

Supports text chat to meet basic communication needs.
Can generate voice dialogues in response to given questions
providing richer interaction experiences.
Utilizes Qwen1.5-32B-Chat as the base model
ensuring high-quality and diverse dialogues.
Fine-tuned through training
making the chatbot closer to Bilibili users' communication habits.
Employs GPT-SoVITS for voice generation
enhancing the naturalness of voice interaction.
Model quantization compression accelerates content generation speed

bilibot is suitable for developers and enterprises that need intelligent chat systems
especially those who want to provide personalized services and enhance user experience. This includes fields like customer service
online education
and entertainment interaction.

As an online customer service representative
providing 24/7 consultation services.
As a smart tutor on an educational platform
assisting with teaching and answering questions.
Providing role-playing and interactive experiences in entertainment applications.

First
visit the bilibot GitHub page and clone or download the project code.
Configure the Python environment according to the project documentation. Anaconda is recommended.
Run the model fine-tuning training and inference testing. Merge the fine-tuned adapters file with the base model.
Use quantization acceleration tools to compress the model to improve generation speed.

Visit

bilibot Visit Over Time

Monthly Visits

494758773

Bounce Rate

37.69%

Page per Visit

5.7

Visit Duration

00:06:29

bilibot Visit Trend

bilibot Visit Geography

bilibot Traffic Sources

bilibot Alternatives

IncarnaMind — Engage in conversations with your documents using large language models like GPT.

Productivity•Machine Learning•PDF

162

CosyVoice — A multilingual large-scale voice generation model, providing full-stack capabilities for inference, training, and deployment.

Others•Multilingual•Voice Generation

3912

Gemini 2.0 Flash Thinking — An AI model developed by Google, offering responses with enhanced reasoning capabilities.

InternationalSelection•Machine Learning•Reasoning

366

Gemini 2.0 Flash Experimental — A high-performance AI model developed by Google DeepMind

InternationalSelection•Machine Learning•Natural Language Processing

150

Astris AI — Astris AI is a division launched by Lockheed Martin that focuses on secure artificial intelligence solutions.

Others•Artificial Intelligence•Machine Learning

Just GPT It — A fun website that imitates ChatGPT.

Entertainment•Artificial Intelligence•Chatbot

126

Phi Open Models — Phi Open Models are powerful, cost-effective, low-latency small language models.

Productivity•Machine Learning•Small Language Models

Recursal AI — Making artificial intelligence accessible

Productivity•Artificial Intelligence•Machine Learning

Nexa — Intelligent AI on enterprise-level devices

Business•On-device AI•Enterprise Solutions

Apollo-LMMs — Exploration of Video Understanding in Large Multimodal Models

Video•Video Understanding•Multimodal Models

RWKV-6 Mixture of Experts — The largest model in the RWKV family, utilizing MoE technology to enhance efficiency.

Programming•Machine Learning•MoE

Q-RWKV-6 32B Instruct Preview — The most powerful variant of the RWKV model, breaking multiple English benchmark tests.

Programming•Machine Learning•Natural Language Processing

CosyVoice Speech Generation Model 2.0-0.5B — Efficient, multilingual speech synthesis model

Music•Speech Synthesis•Artificial Intelligence

180

Command R7B — Fast and Efficient Generative AI Model

Productivity•Machine Learning•Large Language Models

CausVid — A fast causal video generator that enables instant video generation.

Video•Video Generation•Artificial Intelligence

150

Phi-4 — Microsoft's latest small language model focused on complex reasoning.

InternationalSelection•Machine Learning•Language Model

252

tulu-3-sft-olmo-2-mixture — A large-scale multilingual text dataset.

Others•Multilingual•Text Dataset

InternVL 2.5 — Open-source multimodal large language model series

Productivity•multimodal•large language model

Procyon AI Inference Benchmark for Android — A benchmarking tool for measuring AI performance and quality on Android devices.

Others•AI Performance•Benchmarking

Trillium TPU — The sixth-generation Tensor Processing Unit from Google, providing exceptional performance for AI workloads.

Productivity•Machine Learning•High-Performance Computing

OLMo-2-1124-7B-RM — A large language model for text generation and classification.

Productivity•Artificial Intelligence•Natural Language Processing

InternVL2_5-1B — A large multimodal language model that supports image and text understanding.

Image•Multimodal•Large Language Model

SPDL — A thread-based data loading solution that accelerates AI model training.

Productivity•Machine Learning•Data Loading

Best AI Websites & Tools