togethercomputer Goto Github PK

decentralized_training

diffusers

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

examples

repository of example scripts, notebooks, projects

fastertransformer

Transformer related optimization, including BERT, GPT

flash-attention

Fast and memory-efficient exact attention

ft_bloomchat

Transformer related optimization, including BERT, GPT

ft_llama2

Transformer related optimization, including BERT, GPT

ft_redpajama

Transformer related optimization, including BERT, GPT

galai

glm_fastertransformer

GLM with Faster Transformer

gpt-jt-int8

gpt-neox

An implementation of model parallel autoregressive transformers on GPUs, based on the DeepSpeed library.

h3

Together port to run H3

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)

langchain

⚡ Building applications with LLMs through composability ⚡

llama-2-7b-32k-instruct

llamaindex-chatbot

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

llm-awq-ttgi

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

lm-evaluation-harness

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

native_hf_models-slim

open-models-api

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)

openchatkit

opendatahub

port_fastertransformer

Transformer related optimization, including BERT, GPT

quick_deployment_helm

redpajama-data

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

redpajama.cpp

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

sequoia

scalable and robust tree-based speculative decoding algorithm