Phillip Kravtsov's repositories
gan-skeleton
skeleton code for conditional gan training in tensorflow
lit-gpt
Hackable implementation of state-of-the-art open-source LLMs based on nanoGPT. Supports flash attention, 4-bit and 8-bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.
llama.cpp
Port of Facebook's LLaMA model in C/C++
mlab-tools
mlab tools
neural-cube
3x3 rubik's cube solver that uses neural nets as predictors and heuristics
nmep-hw-6
nmep hw 6
openai-cookbook
Examples and guides for using the OpenAI API
qlora
QLoRA: Efficient Finetuning of Quantized LLMs
renegade
On-chain dark pool. MPC for anonymous crosses at midpoint prices.
tensorflow
An Open Source Machine Learning Framework for Everyone
tensorrt
TensorFlow/TensorRT integration
token-transfer
estimate logprobs from one tokenizer under a different tokenizer
transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.