tic-top's repositories
light_strider
Elm-based game (VG100 UMJI)
Adafruit_TouchScreen
STM32 library for 4-wire resistive touchscreens ili9341 (only touch function)
flashattention
flash attention implementation
Smart_follower_pot
EECS373 Project
Bard
Python SDK/API for reverse engineered Google Bard
blog
Public repo for HF blog posts
FastChat
The release repo for "Vicuna: An Open Chatbot Impressing GPT-4"
homepage
Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes
llama2.mojo
Inference Llama 2 in one file of pure 🔥
DeepSpeed
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
gpt-engineer
Specify what you want it to build, the AI asks for clarification, and then builds it.
learn_peft
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
lhbench
Lakehouse storage system benchmark
lora
Using Low-rank adaptation to quickly fine-tune diffusion models.
mamba.py
A simple and efficient Mamba implementation in PyTorch and MLX.
neurobionicspi
Builds a custom Raspberry Pi image for robotics
poe-api
A reverse engineered Python API wrapper for Quora's Poe, which provides free access to ChatGPT, GPT-4, and Claude.
tiktoken
tiktoken is a fast BPE tokeniser for use with OpenAI's models.
tiny-training
On-Device Training Under 256KB Memory [NeurIPS'22]
tinyengine
[NeurIPS 2020] MCUNet: Tiny Deep Learning on IoT Devices; [NeurIPS 2021] MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning; [NeurIPS 2022] MCUNetV3: On-Device Training Under 256KB Memory
transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
vllm
A high-throughput and memory-efficient inference and serving engine for LLMs