vahbuna

zero_to_gpt

Go from no deep learning knowledge to implementing GPT.

DSPy-Indic

This repository implements DSPy programs to tasks in Indian Languages

SpeculativeDecodingPapers

📰 Must-read papers and blogs on Speculative Decoding ⚡️

sglang

SGLang is yet another fast serving framework for large language models and vision language models.

marlin

FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.

cog-whisperspeech

Cog wrapper for collabora/WhisperSpeech

WhisperSpeech

An Open Source text-to-speech system built by inverting Whisper.

genalog

Genalog is an open source, cross-platform python package allowing generation of synthetic document images with custom degradations and text alignment capabilities.

FAVA

deductive-closure

Project page for the Deductive Closure Training.

LLMLingua

To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.

GPTCache

Semantic cache for LLMs. Fully integrated with LangChain and llama_index.

adversarial-machine-learning

Hands-on tutorial on adversarial examples 😈. With Streamlit app ❤️.

notebooks

code for deep learning courses

PMC-LLaMA

The official codes for "PMC-LLaMA: Towards Building Open-source Language Models for Medicine"

deepdoctection

A Repo For Document AI

peft

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

bark

🔊 Text-Prompted Generative Audio Model

jsonformer

A Bulletproof Way to Generate Structured JSON from Language Models

icecube-journal

CLIPA

[NeurIPS 2023] This repository includes the official implementation of our paper "An Inverse Scaling Law for CLIP Training"

iglu-datasets

LLM-As-Chatbot

LLM as a Chatbot Service

uss

guidance

A guidance language for controlling large language models.

seahorse

Seahorse is a dataset for multilingual, multi-faceted summarization evaluation. It consists of 96K summaries with human ratings along 6 quality dimensions: comprehensibility, repetition, grammar, attribution, main idea(s), and conciseness, covering 6 languages, 9 systems and 4 datasets.

Data-Science-Interview-Questions-Answers

Curated list of data science interview questions and answers

LENS

AITemplate

AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (NVIDIA GPU) and MatrixCore (AMD GPU) inference.

fasterText

Library for fast text representation and classification.