Pinned Repositories
ai-toolkit
Various AI scripts. Mostly Stable Diffusion stuff.
alignment-handbook
Robust recipes to align language models with human and AI preferences
anthropic-cookbook
A collection of notebooks/recipes showcasing some fun and effective ways of using Claude.
autofaiss
Automatically create Faiss knn indices with the most optimal similarity search parameters.
chameleon
Repository for Meta Chameleon, a mixed-modal early-fusion foundation model from FAIR.
CLIP-based-NSFW-Detector
cog-flux
Cog inference for flux models
CogVLM
a state-of-the-art-level open visual language model | 多模态预训练模型
Thomaskalnik's Repositories
Thomaskalnik/alignment-handbook
Robust recipes to align language models with human and AI preferences
Thomaskalnik/chameleon
Repository for Meta Chameleon, a mixed-modal early-fusion foundation model from FAIR.
Thomaskalnik/diff-sampler
An open-source toolbox for fast sampling of diffusion models. Official implementations for our [CVPR-2024, ICML-2024] papers
Thomaskalnik/DistillKit
An Open Source Toolkit For LLM Distillation
Thomaskalnik/enroot
A simple yet powerful tool to turn traditional container/OS images into unprivileged sandboxes.
Thomaskalnik/EvolKit
EvolKit is an innovative framework designed to automatically enhance the complexity of instructions used for fine-tuning Large Language Models (LLMs).
Thomaskalnik/flux
Official inference repo for FLUX.1 models
Thomaskalnik/gpt4all
GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.
Thomaskalnik/img2dataset
Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.
Thomaskalnik/kohya_ss
Thomaskalnik/Kolors
Kolors Team
Thomaskalnik/kuberay-helm
Helm charts for the KubeRay project
Thomaskalnik/lfads-torch
A PyTorch implementation of Latent Factor Analysis via Dynamical Systems (LFADS) and AutoLFADS.
Thomaskalnik/llama-recipes
Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment. Demo apps to showcase Meta Llama3 for WhatsApp & Messenger.
Thomaskalnik/llama-stack
Model components of the Llama Stack APIs
Thomaskalnik/llama-stack-apps
Agentic components of the Llama Stack APIs
Thomaskalnik/llm-datasets
High-quality datasets, tools, and concepts for LLM fine-tuning.
Thomaskalnik/locust
Write scalable load tests in plain Python 🚗💨
Thomaskalnik/Lumina-T2X
Lumina-T2X is a unified framework for Text to Any Modality Generation
Thomaskalnik/LyCORIS
Lora beYond Conventional methods, Other Rank adaptation Implementations for Stable diffusion.
Thomaskalnik/MPS
Thomaskalnik/nccl
Optimized primitives for collective multi-GPU communication
Thomaskalnik/oci-hpc-oke
This repo includes everything you need to know about deploying GPU nodes on OCI
Thomaskalnik/OneTrainer
OneTrainer is a one-stop solution for all your stable diffusion training needs.
Thomaskalnik/open_clip
An open source implementation of CLIP.
Thomaskalnik/segment-anything-2
The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
Thomaskalnik/skypilot
SkyPilot: Run AI and batch jobs on any infra (Kubernetes or 12+ clouds). Get unified execution, cost savings, and high GPU availability via a simple interface.
Thomaskalnik/textgrad
Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients.
Thomaskalnik/traefik
The Cloud Native Application Proxy
Thomaskalnik/Vim
Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model