hamidshojanazeri Goto Github PK

alpaca-lora

Instruct-tune LLaMA on consumer hardware

bert-sense

Source code accompanying the KONVENS 2019 paper "Does BERT Make Any Sense? Interpretable Word Sense Disambiguation with Contextualized Embeddings"

chatgpt-pytorch-q-a

cs344_2021

Udacity CS344 Introduction to Parallell Programming (https://classroom.udacity.com/courses/cs344), with assignments/materials updated to build in 2021

deforumstablediffusionlocal

Local version of Deforum Stable Diffusion, supports txt settings file input and animation features!

diffusers

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

disambiguate

Disambiguate is a tool for training and using state of the art neural WSD models

distributed-training

distributed_training

eagle

EAGLE: Lossless Acceleration of LLM Decoding by Feature Extrapolation

examples

A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.

fastertransformer

Transformer related optimization, including BERT, GPT

fsdp_llm

FSDP optimizations for LLM training

fusion

Advanced yet low code framework for fully sharded distributed training

glossbert

GlossBERT: BERT for Word Sense Disambiguation with Gloss Knowledge (EMNLP 2019)

google-research

Google AI Research

gpt-neox

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

h2o

[NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.

hf-tp-inference

PyTorch Native Tensor Parallel for HuggingFace models inference

knowledge-distillation-pytorch

A PyTorch implementation for exploring deep and shallow knowledge distillation (KD) experiments with flexibility

langchain

⚡ Building applications with LLMs through composability ⚡

large-model-inference

llama-adapter

Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters

llama-resources

llm-deployment

llm.c

LLM training in simple, raw C/CUDA

llm_fine_tuning

llm_finetuning_playground

lookaheaddecoding

medusa

Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads