machina-source Goto Github PK

attention-viz

Visualizing query-key interactions in language + vision transformers

chromium

The official GitHub mirror of the Chromium source

evals

Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.

example-react-three-game

fhir-app-starter

flyte

Kubernetes-native workflow automation platform for complex, mission-critical data and ML processes at scale. It has been battle-tested at Lyft, Spotify, Freenome, and others and is truly open-source.

folio-2019

galai

Model API for GALACTICA

gpt-2

Code for the paper "Language Models are Unsupervised Multitask Learners"

llama-models

Utilities intended for use with Llama models.

llm-transparency-tool

LLM Transparency Tool (LLM-TT), an open-source interactive toolkit for analyzing internal workings of Transformer-based language models. *Check out demo at* https://huggingface.co/spaces/facebook/llm-transparency-tool-demo

llm-viz

3D Visualization of an GPT-style LLM

nanogpt

The simplest, fastest repository for training/finetuning medium-sized GPTs.

nnsight

The nnsight package enables interpreting and manipulating the internals of deep learned models.

openai-python

pearl

A Production-ready Reinforcement Learning AI Agent Library brought by the Applied Reinforcement Learning team at Meta.

rgg

sleeper-agents-paper

Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".

swe-bench

[ICLR 2024] SWE-Bench: Can Language Models Resolve Real-world Github Issues?

torchtune

A Native-PyTorch Library for LLM Fine-tuning

transformer-debugger