awesome-repositories.com
Blog
MCP
awesome-repositories.com

Discover the best open-source repositories with AI-powered search.

ExploreCurated searchesOpen-source alternativesSelf-hosted softwareBlogSitemap
ProjectMCP serverAboutHow we rankPress
LegalPrivacyTerms
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
Morizeyao avatar

Morizeyao/GPT2-Chinese

0
View on GitHub↗
7,596 stars·1,683 forks·Python·MIT·28 views

GPT2 Chinese

GPT2-Chinese is a Chinese language model implementation based on the GPT-2 architecture. It provides a causal language model trainer and a natural language generation tool designed for training and generating human-like Chinese text sequences.

The system integrates a BERT tokenizer to process Chinese corpora into manageable units for machine learning. It enables the development of predictive text models that can generate specific patterns, such as news or poetry, through prompt-based text completion.

The project covers a full workflow including text tokenization, model training using a transformer-based decoder, and performance evaluation via perplexity measurement. It also includes utilities for weight-based model serialization to support inference and checkpointing.

Features

  • Decoder Architectures - Implements a GPT-2 based transformer decoder architecture for autoregressive Chinese text generation.
  • Causal - Implements a causal masking mechanism to prevent the model from attending to future tokens during training.
  • Training Pipelines - Provides a complete pipeline for training predictive text models using Chinese datasets.
  • Chinese Natural Language Generation - Generates human-like Chinese text sequences across various styles and genres using a trained GPT-2 model.
  • GPT-2 Implementations - Implements the GPT-2 architecture specifically for training and generating Chinese text.
  • Language Model Training - Develops predictive text models that learn specific patterns like news or poetry from Chinese data.
  • Natural Language Generation - Provides a tool for producing human-like Chinese text based on computational models.
  • Text Tokenization - Provides a BERT-based tokenizer to segment Chinese text into manageable units for machine learning.
  • Text Completion Engines - Functions as a text completion engine that generates logical continuations for Chinese prompts.
  • Causal Language Modeling - Provides a training pipeline based on causal language modeling for next-token prediction.
  • BERT Integrations - Integrates a BERT tokenizer to prepare Chinese corpora for GPT-2 training.
  • Chinese Language Segmenters - Includes specialized tools for tokenizing and segmenting Chinese language corpora.
  • Perplexity Calculators - Calculates perplexity scores to evaluate the predictive accuracy of the trained language model.
  • Model Performance Evaluators - Quantifies model performance using perplexity measurements to evaluate prediction accuracy.
  • Model Implementations - Pre-trained Chinese language model based on GPT-2.
  • Pre-trained Language Models - Code for training GPT-2 on Chinese text.
  • Corpus and Datasets - GPT-2 implementation for Chinese text generation.

Star history

Star history chart for morizeyao/gpt2-chineseStar history chart for morizeyao/gpt2-chinese

How this analysis was created: This summary and feature list are AI-generated from collected project material and can contain mistakes. Stars, license and language are imported from GitHub. Inclusion does not mean that we have tested or audited this project. Check the source documentation for any feature you depend on. Learn more on our About page.

AI search

Explore more awesome repositories

Describe what you need in plain English — the AI ranks thousands of curated open-source projects by relevance.

Start searching with AI

Frequently asked questions

What does morizeyao/gpt2-chinese do?

GPT2-Chinese is a Chinese language model implementation based on the GPT-2 architecture. It provides a causal language model trainer and a natural language generation tool designed for training and generating human-like Chinese text sequences.

What are the main features of morizeyao/gpt2-chinese?

The main features of morizeyao/gpt2-chinese are: Decoder Architectures, Causal, Training Pipelines, Chinese Natural Language Generation, GPT-2 Implementations, Language Model Training, Natural Language Generation, Text Tokenization.

Which projects share features with morizeyao/gpt2-chinese?

Projects with overlapping indexed features include: qwenlm/qwen-7b — Qwen-7B is a pretrained causal language model designed for natural language generation, text processing, and complex… datawhalechina/so-large-lm — This project is a comprehensive educational curriculum and structured learning path covering the full lifecycle of… openai/gpt-2 — This project is a transformer-based language model and autoregressive text generator designed to predict the next… karpathy/build-nanogpt — This is an educational implementation that builds a generative pre-trained transformer (GPT) language model from… deepseek-ai/deepseek-llm — DeepSeek-LLM is a large language model and causal language model designed for natural language generation. It… nndl/llm-beginner — This project is a collection of educational resources and technical guides focused on the development and…

Projects sharing features with GPT2 Chinese

These projects share indexed features with GPT2 Chinese. Shared tags can include platform or build tooling; verify the primary use case before treating a result as a replacement.
  • qwenlm/qwen-7bQwenLM avatar

    QwenLM/Qwen-7B

    21,343View on GitHub↗

    Qwen-7B is a pretrained causal language model designed for natural language generation, text processing, and complex reasoning tasks. It is available as an instruction-tuned model optimized for conversational interactions and a tool-use model capable of executing function calls and interacting with external APIs. The project provides a quantized version of the model to reduce GPU memory usage and supports the development of autonomous agents that can execute code and perform functions to complete complex goals. The system covers a wide range of capabilities including model fine-tuning throug

    Python
    View on GitHub↗21,343
  • datawhalechina/so-large-lmdatawhalechina avatar

    datawhalechina/so-large-lm

    7,400View on GitHub↗

    This project is a comprehensive educational curriculum and structured learning path covering the full lifecycle of large language models. It provides a guided progression through the theory, architecture, training, and deployment of these models. The curriculum includes specialized guides on transformer architecture, model training tutorials, and frameworks for designing autonomous agents. It also provides dedicated resources for studying model safety and ethics. The material covers a wide range of technical capabilities, including distributed training strategies, parameter-efficient fine-tu

    View on GitHub↗7,400
  • openai/gpt-2openai avatar

    openai/gpt-2

    24,967View on GitHub↗

    This project is a transformer-based language model and autoregressive text generator designed to predict the next token in a sequence to produce human-like prose and synthetic text. It functions as a large language model that utilizes a transformer architecture to learn linguistic patterns from large datasets for unsupervised multitask learning. The repository provides a distribution of pre-trained weights, enabling natural language processing tasks without requiring additional training. This allows the model to perform zero-shot task generalization by applying learned patterns to new tasks.

    Python
    View on GitHub↗24,967
  • karpathy/build-nanogptkarpathy avatar

    karpathy/build-nanogpt

    4,746View on GitHub↗

    This is an educational implementation that builds a generative pre-trained transformer (GPT) language model from scratch using PyTorch. The project is structured as a step-by-step tutorial, walking through the construction of a decoder-only transformer architecture and its training loop with clean git commits and an accompanying video lecture for a hands-on learning experience. What sets this implementation apart is its focus on practical reproduction: it provides a workflow to train a 124-million-parameter model from scratch in about one hour on cloud GPU hardware, costing under ten dollars.

    Python
    View on GitHub↗4,746
  • Compare all 30 related projects→