Richard Kelley's repositories
open-source-rover
A build-it-yourself, 6-wheel rover based on the rovers on Mars!
Livox_Color_View_And_Mpping
A module to color the Livox Frame and FASTLIO2's map, inorder to checkout our extrinsicT ~
Copyisallyouneed
Codebase for Copy-Generator model, including an implementation of kNN-LM
kr_autonomous_flight
KR (KumarRobotics) autonomous flight system for GPS-denied quadrotors
bark
🔊 Text-Prompted Generative Audio Model
DeepSpeed
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
lit-llama
Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, quantization, LoRA fine-tuning, pre-training. Apache 2.0-licensed.
alpaca-lora
Instruct-tune LLaMA on consumer hardware
RWKV-LM
RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.
ReAct
[ICLR 2023] ReAct: Synergizing Reasoning and Acting in Language Models
awesome-marketing-datascience
Collection of useful Datascience things across the web
LoRA
Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"
bus_mapper
Code for building maps on the RTC bus.
stanford_alpaca
Code and documentation to train Stanford's Alpaca models, and generate the data.
cs6120
advanced compilers
FlexGen
Throughput-oriented systems for large language models on commodity GPUs.
Prompt-Engineering-Guide
:octopus: Guides, papers, lecture, and resources for prompt engineering
pypose
To connect classic robotics with modern learning methods seamlessly.
mlcc
Fast and Accurate Extrinsic Calibration for Multiple LiDARs and Cameras
roadside_lidar
Controller for a distributed municipal-scale lidar network.
diplomacy_cicero
Code for Cicero, an AI agent that plays the game of Diplomacy with open-domain natural language negotiation.
li_slam_ros2
ROS2 package of tightly-coupled lidar inertial ndt/gicp slam
gpt-2
Code for the paper "Language Models are Unsupervised Multitask Learners"
FP16
Conversion to/from half-precision floating point formats
BALM
An efficient and consistent bundle adjustment for lidar mapping
prompt-engine
A library for helping developers craft prompts for Large Language Models
ALSO
ALSO: Automotive Lidar Self-supervision by Occupancy estimation
engine-sim
Combustion engine simulator that generates realistic audio.
FAST_LIO_LC
The tight integration of FAST-LIO with Radius-Search-based loop closure module.