AkimfromParis

ngram

The n-gram Language Model

LLM101n

LLM101n: Let's build a Storyteller

gs-quant

Python toolkit for quantitative finance

lectures

Material for cuda-mode lectures

Bend

A massively parallel, high-level programming language

axolotl

Go ahead and axolotl questions

ThunderKittens

Tile primitives for speedy kernels

guardrails

Adding guardrails to large language models.

japanese-lm-fin-harness

Japanese Language Model Financial Evaluation Harness

unsloth

Finetune Llama 3, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

bpr

Binary Passage Retriever (BPR) - an efficient passage retriever for open-domain question answering

cohere-toolkit

Cohere Toolkit is a collection of prebuilt components enabling users to quickly build and deploy RAG applications.

symbolicai

Compositional Differentiable Programming Library

llama2.c

Inference Llama 2 in one file of pure C

outlines

Structured Text Generation

llm_slerp_generation

Repo hosting codes and materials related to speeding LLMs' generative abilities while preserving quality using token merging.

llm.c

LLM training in simple, raw C/CUDA

llm-leaderboard

Project of llm evaluation to Japanese tasks

mergekit

Tools for merging pretrained large language models.

AdamergeX

evolutionary-model-merge

Official repository of Evolutionary Optimization of Model Merging Recipes

RAGatouille

Easily use and train state of the art late-interaction retrieval methods (ColBERT) in any RAG pipeline. Designed for modularity and ease-of-use, backed by research.

camelot

A Python library to extract tabular data from PDFs

unstructured

Open source libraries and APIs to build custom preprocessing pipelines for labeling, training, or production machine learning pipelines.

pgvecto.rs

Scalable, Low-latency and Hybrid-enabled Vector Search in Postgres. Revolutionize Vector Search, not Database.

pgvector

Open-source vector similarity search for Postgres

sentence-transformers

Multilingual Sentence & Image Embeddings with BERT

faiss

A library for efficient similarity search and clustering of dense vectors.

llama_index

LlamaIndex is a data framework for your LLM applications

AutoGPTQ

An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.