lesterpjy
Follow
Stars
Clean, minimal, accessible reproduction of DeepSeek R1-Zero
An extremely fast Python package and project manager, written in Rust.
Get up and running with Llama 3.3, DeepSeek-R1, Phi-4, Gemma 2, and other large language models.
Data and tools for generating and inspecting OLMo pre-training data.
Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.
Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting yo…
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
Tutorials on implementing a few sequence-to-sequence (seq2seq) models with PyTorch and TorchText.
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
A Gradio web UI for Large Language Models with support for multiple inference backends.
Examples and guides for using the OpenAI API
GPT4 & LangChain Chatbot for large PDF docs
Must-read papers on prompt-based tuning for pre-trained language models.
🐙 Guides, papers, lecture, notebooks and resources for prompt engineering
Open source libraries and APIs to build custom preprocessing pipelines for labeling, training, or production machine learning pipelines.
Nodejs extension host for vim & neovim, load extensions like VSCode and host language servers.
A playbook for systematically maximizing the performance of deep learning models.
This repo includes ChatGPT prompt curation to use ChatGPT and other LLM tools better.
🦜🔗 Build context-aware reasoning applications
DSPy: The framework for programming—not prompting—language models
Practice your pandas skills!
Sentiment Analysis, Text Classification, Text Augmentation, Text Adversarial defense, etc.;
Fengshenbang-LM(封神榜大模型)是IDEA研究院认知计算与自然语言研究中心主导的大模型开源体系，成为中文AIGC和认知智能的基础设施。
Dataframes powered by a multithreaded, vectorized query engine, written in Rust