reshinthadithyan Goto Github PK

goosebox

sandboxed eval server for running code snippets

gorilla

Gorilla: An API store for LLMs

gpt-code-clippy

Full description can be found here: https://discuss.huggingface.co/t/pretrain-gpt-neo-for-open-source-github-copilot-model/7678?u=ncoop57

gpt-fast

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

gpt-neox

An implementation of model parallel autoregressive transformers on GPUs, based on the DeepSpeed library.

grok-1

Grok open release

helm

Holistic Evaluation of Language Models (HELM), a framework to increase the transparency of language models (https://arxiv.org/abs/2211.09110).

hf_jax_transcoder_mini

A Minimal version of Transcoder built with Jax

interpreter_grounded_codelms

llava

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

lm-evaluation-harness

A framework for few-shot evaluation of autoregressive language models.

lm_dataformat

longalign

LongAlign: A Recipe for Long Context Alignment Encompassing Data, Training, and Evaluation

maxtext

A simple, performant and scalable Jax LLM!

midi-communicator

Utils for Midi to act as a keyboard

mlx-examples

Examples in the MLX framework

nanogpt

The simplest, fastest repository for training/finetuning medium-sized GPTs.

nanotron

Minimalistic large language model 3D-parallelism training

penzai

A JAX research toolkit for building, editing, and visualizing neural networks.

pile-v2-hasher

pilev2

pretty-midi

Utility functions for handling MIDI data in a nice/intuitive way.

probable-guacamole

probes

Probing pre-trained source code models

python-graphs

A static analysis library for computing graph representations of Python programs suitable for use with graph neural networks.

pytorch-geometric-with-pytorch-lightning

Basic example onto the way Pytorch Geometric can be used with Pytorch Lightning.

pytorch_basics

pytorch_geometric

Graph Neural Network Library for PyTorch

qdsyntheticdata

reading-group

Information about the CodedotAI reading group sessions.