Will Thompson (will-thompson-k)

will-thompson-k

Geek Repo

Company:@tempuslabs

Home Page:https://willthompson.name

Twitter:@will_thompson_k

Github PK Tool:Github PK Tool

Will Thompson's repositories

mistral_7b_lora_example

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

Language:PythonLicense:MITStargazers:1Issues:2Issues:0

alignment-handbook

Robust recipes to align language models with human and AI preferences

Language:PythonLicense:Apache-2.0Stargazers:0Issues:1Issues:0
Language:PythonStargazers:0Issues:0Issues:0

axolotl

Go ahead and axolotl questions

Language:PythonLicense:Apache-2.0Stargazers:0Issues:0Issues:0

chain-of-verification

This repository implements the chain of verification paper by Meta AI

Language:PythonStargazers:0Issues:1Issues:0

deepchem

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

Language:PythonLicense:MITStargazers:0Issues:1Issues:0

DNA-Diffusion

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

Language:Jupyter NotebookLicense:MITStargazers:0Issues:0Issues:0

flash-attention

Fast and memory-efficient exact attention

Language:PythonLicense:BSD-3-ClauseStargazers:0Issues:0Issues:0

generative_agents

Generative Agents: Interactive Simulacra of Human Behavior

License:Apache-2.0Stargazers:0Issues:0Issues:0

gpt-engineer

Specify what you want it to build, the AI asks for clarification, and then builds it.

Language:PythonLicense:MITStargazers:0Issues:0Issues:0

jax-triton

jax-triton contains integrations between JAX and OpenAI Triton

Language:PythonLicense:Apache-2.0Stargazers:0Issues:0Issues:0

langchain

⚡ Building applications with LLMs through composability ⚡

Language:PythonLicense:MITStargazers:0Issues:1Issues:0

neurips_llm_efficiency_challenge

NeurIPS Large Language Model Efficiency Challenge: 1 LLM + 1GPU + 1Day

Language:PythonStargazers:0Issues:1Issues:0

cv

Print-friendly, minimalist CV page

Language:TypeScriptLicense:MITStargazers:0Issues:0Issues:0

dont_know_jax

learning jax

License:MITStargazers:0Issues:0Issues:0

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.

License:Apache-2.0Stargazers:0Issues:0Issues:0

LLM-Benchmark-Logs

Just a bunch of benchmark logs for different LLMs

License:MITStargazers:0Issues:0Issues:0

llm-swarm

Manage scalable open LLM inference endpoints in Slurm clusters

License:MITStargazers:0Issues:0Issues:0

llm_steer

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

License:MITStargazers:0Issues:0Issues:0

LoRA

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

Language:PythonLicense:MITStargazers:0Issues:1Issues:0

micrograd

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

License:MITStargazers:0Issues:0Issues:0

mistral-src

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

License:Apache-2.0Stargazers:0Issues:0Issues:0

open_spiel

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

Language:C++License:Apache-2.0Stargazers:0Issues:1Issues:0

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.

License:Apache-2.0Stargazers:0Issues:0Issues:0

torchtitan

A native PyTorch Library for large model training

License:BSD-3-ClauseStargazers:0Issues:0Issues:0
License:MITStargazers:0Issues:0Issues:0

vllm

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

License:Apache-2.0Stargazers:0Issues:0Issues:0

vocode-python

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

Language:PythonLicense:MITStargazers:0Issues:1Issues:0
License:MITStargazers:0Issues:0Issues:0

xformers

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

License:NOASSERTIONStargazers:0Issues:0Issues:0