Mihaiii

Mihaiii's Stars

• dabochen/spreadsheet-is-all-you-need

  A nanoGPT pipeline packed in a spreadsheet

  2.1k121

• karpathy/LLM101n

  LLM101n: Let's build a Storyteller

  30.4k1.7k

• ironjr/grokfast

  Official repository for the paper "Grokfast: Accelerated Grokking by Amplifying Slow Gradients"

  Language:Python52344

• andyrdt/refusal_direction

  Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".

  Language:Python13227

• xhluca/bm25s

  Fast lexical search implementing BM25 in Python using Numpy, Numba and Scipy

  Language:Python92440

• wejoncy/QLLM

  A general 2-8 bits quantization toolbox with GPTQ/AWQ/HQQ, and export to onnx/onnx-runtime easily.

  Language:Python15015

• fchollet/ARC-AGI

  The Abstraction and Reasoning Corpus

  Language:JavaScript3.6k596

• nivibilla/build-nanogpt

  Video+code lecture on building nanoGPT from scratch

  Language:Python6411

• microsoft/Samba

  Official implementation of "Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling"

  Language:Python80949

• karpathy/build-nanogpt

  Video+code lecture on building nanoGPT from scratch

  Language:Python3.7k511

• ltgoslo/bert-in-context

  Official implementation of "BERTs are Generative In-Context Learners"

  Language:Python19

• google/mesop

  Rapidly build AI apps in Python

  Language:Python5.7k276

• modal-labs/llm-finetuning

  Guide for fine-tuning Llama/Mistral/CodeLlama models and more

  Language:Python54084

• aboros98/synth

  synth. is a framework designed for the generation of synthetic instructions to enhance LLM training.

  Language:Python82

• llm-merging/LLM-Merging

  LLM-Merging: Building LLMs Efficiently through Merging

  Language:Jupyter Notebook17641

• opea-project/GenAIExamples

  Generative AI Examples is a collection of GenAI examples such as ChatQnA, Copilot, which illustrate the pipeline capabilities of the Open Platform for Enterprise AI (OPEA) project.

  Language:Shell287195

• pyeventsourcing/eventsourcing

  A library for event sourcing in Python.

  Language:Python1.5k129

• parlance-labs/ftcourse

  Language:Jupyter Notebook16338

• 2noise/ChatTTS

  A generative speech model for daily dialogue.

  Language:Python32.8k3.6k

• jjallaire/inspect-llm-workshop

  Language:Python4810

• terrierteam/ir_measures

  provides a common interface to many IR measure tools

  Language:Python808

• modal-labs/modal-examples

  Examples of programs built using Modal

  Language:Python741178

• amack315/unsupervised-steering-vectors

  Language:Jupyter Notebook277

• iamgroot42/mimir

  Python package for measuring memorization in LLMs.

  Language:Jupyter Notebook12523

• nrimsky/CAA

  Steering Llama 2 with Contrastive Activation Addition

  Language:Jupyter Notebook10431

• johnowhitaker/agent-openai-python-prompty

  A creative writing multi-agent solution to help users write articles.

  1

• FailSpy/abliterator

  Simple Python library/structure to ablate features in LLMs which are supported by TransformerLens

  Language:Python34845

• naklecha/llama3-from-scratch

  llama3 implementation one matrix multiplication at a time

  Language:Jupyter Notebook13.8k1.1k

• OpenLLM-Ro/llama-recipes

  Language:Python204

• nickmitchko/llm_steer-oobabooga

  Steer LLM outputs towards a certain topic/subject and enhance response capabilities using activation engineering by adding steering vectors, now in oobabooga text generation webui!

  Language:Jupyter Notebook11