giulio98

giulio98's Stars

• dottxt-ai/outlines

  Structured Text Generation

  Language:Python8.8k439

• TransformerLensOrg/TransformerLens

  A library for mechanistic interpretability of GPT-style language models

  Language:Python1.5k291

• MustaphaBounoua/soi

  SΩI: Score-based O-INFORMATION Estimation

  Language:Python6

• crowsonkb/k-diffusion

  Karras et al. (2022) diffusion models for PyTorch

  Language:Python2.3k376

• rtaiello/let_them_drop

  Official Repository of the paper "Let Them Drop: Scalable and Efficient Secure Federated Learning Solutions Agnostic to Client Stragglers "

  Language:Python4

• mspronesti/llm.sycl

  llm.c, but in SYCL/Intel oneAPI!

  Language:C++5

• lulor/npgrad

  Simple autodiff library built on NumPy, inspired by micrograd

  Language:Python1

• facebookresearch/xformers

  Hackable and optimized Transformers building blocks, supporting a composable construction.

  Language:Python8.5k607

• meta-llama/llama3

  The official Meta Llama 3 GitHub site

  Language:Python26.7k3k

• huggingface/datatrove

  Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.

  Language:Python2k142

• karpathy/llama2.c

  Inference Llama 2 in one file of pure C

  Language:C17.3k2.1k

• MustaphaBounoua/minde

  Official implementation of MINDE: Mutual Information Neural Diffusion Estimation

  Language:Python102

• rtaiello/glucose-prediction

  Language:Python3

• facebookresearch/hydra

  Hydra is a framework for elegantly configuring complex applications

  Language:Python8.7k628

• SqueezeAILab/SqueezeLLM

  [ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization

  Language:Python63743

• ray-project/ray

  Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

  Language:Python33.5k5.7k

• vllm-project/vllm

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

  Language:Python28.8k4.3k

• mit-han-lab/streaming-llm

  [ICLR 2024] Efficient Streaming Language Models with Attention Sinks

  Language:Python6.6k362

• tranbahien/data-mollification

  One-Line-of-Code Data Mollification Improves Optimization of Likelihood-based Generative Models (NeurIPS 2023)

  Language:Jupyter Notebook2

• jessevig/bertviz

  BertViz: Visualize Attention in NLP Models (BERT, GPT2, BART, etc.)

  Language:Python6.9k775

• rtaiello/pp_dipy

  Extension of Dipy with Privacy Enhancing Technologies

  Language:Python1

• yuvalkirstain/PickScore

  Language:Python42925

• haoliuhl/ringattention

  Transformers with Arbitrarily Large Context

  Language:Python62848

• huggingface/text-embeddings-inference

  A blazing fast inference solution for text embeddings models

  Language:Rust2.7k173

• huggingface/text-generation-inference

  Large Language Model Text Generation Inference

  Language:Python8.9k1.1k

• marella/ctransformers

  Python bindings for the Transformer models implemented in C/C++ using GGML library.

  Language:C1.8k137

• Chainlit/chainlit

  Build Conversational AI in minutes ⚡️

  Language:Python7k923

• fetchai/agents-aea

  A framework for autonomous economic agent (AEA) development

  Language:Python20661

• ooddb/OODDB

  OOD Detection Benchmark

  Language:Python2

• GaParmar/clean-fid

  PyTorch - FID calculation with proper image resizing and quantization steps [CVPR 2022]

  Language:Python94872