Together

OpenChatKit

RedPajama-Data

The RedPajama-Data repository contains code for preparing large datasets for training large language models.

stripedhyena

Repository for StripedHyena, a state-of-the-art beyond Transformer architecture

redpajama.cpp

Extend the original llama.cpp repo to support redpajama model.

Llama-2-7B-32K-Instruct

llamaindex-chatbot

A RAG Chatbot with Next.js, Together.ai and Llama Index

together-python

The Official Python Client for Together's API

Quick_Deployment_HELM

diffusers

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch

transformers_port

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

FT_Llama2

Transformer related optimization, including BERT, GPT

UniversalSD

Universal Stable Diffusion Pipeline(s) with Flash Attention

examples

repository of example scripts, notebooks, projects

together-worker

utilities for workers

flash-attention

Fast and memory-efficient exact attention

FT_Redpajama

Transformer related optimization, including BERT, GPT

H3

Together port to run H3

langchain

⚡ Building applications with LLMs through composability ⚡

llm-awq-ttgi

AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

native_hf_models-slim

together-chat

Streamlit Component, for a Chatbot UI

vllm

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

vllm-ttgi

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

FasterTransformer

Transformer related optimization, including BERT, GPT

helm

Holistic Evaluation of Language Models (HELM), a framework to increase the transparency of language models (https://arxiv.org/abs/2211.09110).

js-eventsource

EventSource client for Node.js and Browser (polyfill)

lm-evaluation-harness

A framework for few-shot evaluation of autoregressive language models.

openapi

An OpenAPI API specifications file describes an API in its entirety and are typically written in YAML or JSON. including: Endpoints: which are available (/users) and operations on each (GET /users, POST /users) Authentication methods. Operation parameters for each operation (Input and output)

Sequoia

scalable and robust tree-based speculative decoding algorithm

TensorRT-LLM

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.