younesbelkada

interfacegan

InterfaceGAN++: Exploring the limits of InterfaceGAN. In this repository, we propose an approach, termed as InterFaceGAN++, for semantic face editing based on the work from Shen et al. Specifically, we leverage the ideas from the previous work, by applying the method for new face attributes, and also for StyleGAN3. We qualitatively explain that moving the latent vector toward the trained boundaries leads in many cases to keeping the semantic information of the generated images (by preserving its local structure) and modify the desired attribute, thus helps to demonstrate the disentangled property of the StyleGANs.

transformers

🤗 Transformers: State-of-the-art Natural Language Processing for TensorFlow 2.0 and PyTorch.

DataDreamer

Prompt. Generate Synthetic Data. Train & Align Models. 🤖💤

vllm

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

AutoGPTQ

An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.

axolotl

Go ahead and axolotl questions

llama.cpp

LLM inference in C/C++

mlx

MLX: An array framework for Apple silicon

needle-in-a-haystack

Doing simple retrieval from LLM models at various context lengths to measure accuracy

optimum

🏎️ Accelerate training and inference of 🤗 Transformers with easy to use hardware optimization tools

peft

Parameter-Efficient Fine-Tuning

starter-academic

tokenizer-viz

Simple tool to allow for HTML visualization of tokenization boundaries.

BakLLaVA

bigcode-evaluation-harness

A framework for the evaluation of autoregressive code generation language models.

BitNet

Official inference framework for 1-bit LLMs

blog

Public repo for HF blog posts

diffusers

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

EETQ

Easy and Efficient Quantization for Transformers

fsdp_qlora

Training LLMs with QLoRA + FSDP

lighteval

Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends

LLaMA-Factory

Easy-to-use LLM fine-tuning framework (LLaMA, BLOOM, Mistral, Baichuan, Qwen, ChatGLM)

llm-awq

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

LOMO

LOMO: LOw-Memory Optimization

mamba

Mamba SSM architecture

mlx-examples

Examples in the MLX framework

quanto

A pytorch Quantization Toolkit

test-dummy

text-generation-webui

A Gradio web UI for Large Language Models. Supports transformers, GPTQ, AWQ, EXL2, llama.cpp (GGUF), Llama models.

unsloth

5X faster 60% less memory QLoRA finetuning