rocke2020

tiktoken

tiktoken is a fast BPE tokeniser for use with OpenAI's models.

wttr.in

:partly_sunny: The right way to check the weather

ChatGLM-6B

ChatGLM-6B: An Open Bilingual Dialogue Language Model | 开源双语对话语言模型

llamafile

Distribute and run LLMs with a single file.

loguru

Python logging made (stupidly) simple

ChatGLM3

ChatGLM3 series: Open Bilingual Chat LLMs | 开源双语对话语言模型

weblangchain_chatglm

Retrieval Augmented Generation (RAG) implementation through libraries like Tavily, LangChain, ChatGLM3

PeptideBERT

Transformer Based Language Model for Peptide Property Prediction

pydantic-settings

Settings management using pydantic

localLLM_guidance

Local LLM ReAct Agent with Guidance

guidance

A guidance language for controlling large language models.

BrainChulo

Harnessing the Memory Power of the Camelids

pyserini

Pyserini is a Python toolkit for reproducible information retrieval research with sparse and dense representations.

rank_bm25

A Collection of BM25 Algorithms in Python

dl_binder_design

af2seq

hdbscan

A high performance implementation of HDBSCAN clustering.

WindTerm

A professional cross-platform SSH/Sftp/Shell/Telnet/Serial terminal.

GNNPapers

Must-read papers on graph neural networks (GNN)

einops

Flexible and powerful tensor operations for readable and reliable code (for pytorch, jax, TF and others)

DeepNeuropePred

DeepNeuropePred：a robust tool to predict cleavage sites in neuropeptide precursors

NeuroPred-PLM

neuropeptide prediction

private-gpt

Interact with your documents using the power of GPT, 100% privately, no data leaks

llama.cpp

LLM inference in C/C++

llama-cpp-python

Python bindings for llama.cpp

AMAnD

A pythonic DeepSVDD pipeline to create models that flag anomalies in metagenomic samples

DeepSpeed-MII

MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.

magicoder

Magicoder: Source Code Is All You Need

langchain

🦜🔗 Build context-aware reasoning applications

vllm

A high-throughput and memory-efficient inference and serving engine for LLMs