samsja's repositories
pydantic_config
Manage ML configuration with pydantic
samsja.github.io
repo for github page files
llama-jaxtyping
LLaMa implementation fork from lit-llama fully typed with jaxtyping
open-flamingo-serve
Serve Open Flamingo via gRPC
image_retrieval
Model and training recipe for image retrieval. Both selfsupervised and supervised learning
reason_net
bigger context window, less weight = good local model
belote_libre_v2
Mono repo for Belote libre v2: Implementation of a open source version of the french game Belote.
bitsandbytes
8-bit CUDA functions for PyTorch
minGPT
A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training
msn
Masked Siamese Networks for Label-Efficient Learning (https://arxiv.org/abs/2204.07141)
ndarray
ndarray: an N-dimensional array with array views, multidimensional slicing, and efficient operations
peft
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
penzai
A JAX research toolkit for building, editing, and visualizing neural networks.
pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
simsiam
FORK of PyTorch implementation of SimSiam https//arxiv.org/abs/2011.10566
stable-diffusion
A latent text-to-image diffusion model
tabby
Self-hosted AI coding assistant
torchtitan
A native PyTorch Library for large model training
typing_inspect
Runtime inspection utilities for Python typing module