PandasAI is the Python library that integrates Gen AI into pandas, making data analysis conversational

A component that allows you to place a navigation bar in your Streamlit app.

OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models

A secure authentication module to validate user credentials in a Streamlit application.

Efficient Triton Kernels for LLM Training

Implementing MinBPE training on GCP DataProc (serverless spark on GCP)

Align the token outputs from Spacy and Huggingface to help understand what language structures transformers see

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

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

Pretrain, finetune, deploy 20+ LLMs on your own data. Uses state-of-the-art techniques: flash attention, FSDP, 4-bit, LoRA, and more.

Agency Theme for Jekyll

Evaluate the accuracy of LLM generated outputs

This is a 300M MicroLlama version of TinyLlama

Neumorphism designed Jekyll theme for personal websites, portfolios and resumes.

Data and tools for generating and inspecting OLMo pre-training data.

Online playground for OpenAPI tokenizers

Modeling, training, eval, and inference code for OLMo

MobiLlama : Small Language Model tailored for edge devices

Toolkit for creating, sharing and using natural language prompts.

A unified evaluation framework for large language models

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

Data preparation code for Amber 7B LLM

A template repo for Python packages from AllenAI

Multilingual Sentence & Image Embeddings with BERT