dsindex

gpt-crawler

Crawl a site to generate knowledge files to create your own custom GPT from a URL

sentence-transformers

Multilingual Sentence & Image Embeddings with BERT

mamba

Mamba SSM architecture

ml-ferret

PowerInfer

High-speed Large Language Model Serving on PCs with Consumer-grade GPUs

rags

Build ChatGPT over your data, all with natural language

LLMLingua

To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.

mamba-minimal

Simple, minimal implementation of the Mamba SSM in one file of PyTorch.

prompt2model

prompt2model - Generate Deployable Models from Natural Language Instructions

KwaiAgents

A generalized information-seeking agent system with Large Language Models (LLMs).

ATLAS

A principled instruction benchmark on formulating effective queries and prompts for large language models (LLMs). Our paper: https://arxiv.org/abs/2312.16171

GPT-RAG

Sharing the learning along the way we been gathering to enable Azure OpenAI at enterprise scale in a secure manner. GPT-RAG core is a Retrieval-Augmented Generation pattern running in Azure, using Azure Cognitive Search for retrieval and Azure OpenAI large language models to power ChatGPT-style and Q&A experiences.

mamba-chat

Mamba-Chat: A chat LLM based on the state-space model architecture 🐍

HALOs

A library with extensible implementations of DPO, KTO, PPO, ORPO, and other human-aware loss functions (HALOs).

LLM-Shearing

[ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning

textbook_quality

Generate textbook-quality synthetic LLM pretraining data

deita

Deita: Data-Efficient Instruction Tuning for Alignment [ICLR2024]

MathPile

Generative AI for Math: MathPile

galactic

data cleaning and curation for unstructured text

RetNet

Huggingface compatible implementation of RetNet (Retentive Networks, https://arxiv.org/pdf/2307.08621.pdf) including parallel, recurrent, and chunkwise forward.

sodaverse

🥤🧑🏻‍🚀Code and dataset for our EMNLP 2023 paper - "SODA: Million-scale Dialogue Distillation with Social Commonsense Contextualization"

T-Eval

[ACL2024] T-Eval: Evaluating Tool Utilization Capability of Large Language Models Step by Step

EETQ

Easy and Efficient Quantization for Transformers

TACO

MetaTool

[ICLR 2024] MetaTool Benchmark for Large Language Models: Deciding Whether to Use Tools and Which to Use

mixtral_ollama

TrFr

Truth Forest: Toward Multi-Scale Truthfulness in Large Language Models through Intervention without Tuning

vertex-gemini

mixtral-vis-moe

Visualize expert firing frequencies across sentences in the Mixtral MoE model

Data_StrategyQA

StrategyQA 데이터 세트 번역