tianyil1 Goto Github PK

albert

ALBERT: A Lite BERT for Self-supervised Learning of Language Representations

alpaca-lora

Instruct-tune LLaMA on consumer hardware

colossalai

Making large AI models cheaper, faster and more accessible

cream

This is a collection of our NAS and Vision Transformer work.

credit-card-fraud-detection

deepspeed

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

e2eaiok

fastchat

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and FastChat-T5.

genaicomps

GenAI components at micro-service level; GenAI service composer to create mega-service

genaiexamples

Intel Generative AI Examples (e.g., ChatQnA with RAG) on Xeon and Gaudi2

gpt-3

GPT-3: Language Models are Few-Shot Learners

gpt-4-llm

graph-neural-networks-and-analytics

horovod

Distributed training framework for TensorFlow, Keras, PyTorch, and Apache MXNet.

intel-extension-for-pytorch

A Python package for extending the official PyTorch that can easily obtain performance on Intel platform

langchain

🦜🔗 Build context-aware reasoning applications

langchain-chatbot

Examples of chatbot implementations with Langchain and Streamlit

llama

Inference code for LLaMA models

llama2.c

Inference Llama 2 in one file of pure C

llama_index

LlamaIndex (formerly GPT Index) is a data framework for your LLM applications

llm-on-ray

Pretrain, finetune and serve LLMs on Intel platforms with Ray

lm-evaluation-harness

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

megatron-lm

Ongoing research training transformer models at scale

metagpt

🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming

models

Model Zoo for Intel® Architecture: contains Intel optimizations for running deep learning workloads on Intel® Xeon® Scalable processors

morpheus

Morpheus SDK

nemo

NeMo: a toolkit for conversational AI

neural-compressor

Intel® Neural Compressor (formerly known as Intel® Low Precision Optimization Tool), targeting to provide unified APIs for network compression technologies, such as low precision quantization, sparsity, pruning, knowledge distillation, across different deep learning frameworks to pursue optimal inference performance.

nlp-architect

A model library for exploring state-of-the-art deep learning topologies and techniques for optimizing Natural Language Processing neural networks

peft

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.