will-thompson-k

alignment-handbook

Robust recipes to align language models with human and AI preferences

AlpaCare

axolotl

Go ahead and axolotl questions

babyagi

deeplearning-nlp-models

A small, interpretable codebase containing the re-implementation of a few "deep" NLP models in PyTorch. Colab notebooks to run with GPUs. Models: word2vec, CNNs, transformer, gpt.

microstructure-plotter

visualize financial microstructure 📈 & debug trading bots 🤖

mistral_7b_lora_example

A simple example illustrating how to fine-tune Mistal7b via (q)LoRA

tldr-transformers

The "tl;dr" on a few notable transformer papers (pre-2022).

will-thompson-k/mistral_7b_lora_example

A simple example illustrating how to fine-tune Mistal7b via (q)LoRA

will-thompson-k/alignment-handbook

Robust recipes to align language models with human and AI preferences

will-thompson-k/AlpaCare

will-thompson-k/axolotl

Go ahead and axolotl questions

will-thompson-k/chain-of-verification

This repository implements the chain of verification paper by Meta AI

will-thompson-k/deepchem

Democratizing Deep-Learning for Drug Discovery, Quantum Chemistry, Materials Science and Biology

will-thompson-k/DNA-Diffusion

🧬 Understanding the code of life: Generative modeling of regulatory DNA sequences with diffusion probabilistic models 💨

will-thompson-k/flash-attention

Fast and memory-efficient exact attention

will-thompson-k/generative_agents

Generative Agents: Interactive Simulacra of Human Behavior

will-thompson-k/jax-triton

jax-triton contains integrations between JAX and OpenAI Triton

will-thompson-k/langchain

⚡ Building applications with LLMs through composability ⚡

will-thompson-k/cv

Print-friendly, minimalist CV page

will-thompson-k/dont_know_jax

learning jax

will-thompson-k/langgraph

Build resilient language agents as graphs.

will-thompson-k/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.

will-thompson-k/LLM-Benchmark-Logs

Just a bunch of benchmark logs for different LLMs

will-thompson-k/llm-swarm

Manage scalable open LLM inference endpoints in Slurm clusters

will-thompson-k/llm_steer

Steer LLM outputs towards a certain topic/subject and enhance response capabilities using activation engineering by adding steering vectors

will-thompson-k/LoRA

Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

will-thompson-k/micrograd

A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API

will-thompson-k/mistral-src

Reference implementation of Mistral AI 7B v0.1 model.

will-thompson-k/nano-llama31

nanoGPT style version of Llama 3.1

will-thompson-k/open_spiel

OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.

will-thompson-k/paxml

Pax is a Jax-based machine learning framework for training large scale models. Pax allows for advanced and fully configurable experimentation and parallelization, and has demonstrated industry leading model flop utilization rates.

will-thompson-k/torchtitan

A native PyTorch Library for large model training

will-thompson-k/transformer-debugger

will-thompson-k/vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

will-thompson-k/vocode-python

🤖 Build voice-based LLM agents. Modular + open source.

will-thompson-k/weak-to-strong

will-thompson-k/xformers

Hackable and optimized Transformers building blocks, supporting a composable construction.