cm2435

minGPT

A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

sentence-transformers

Multilingual Sentence & Image Embeddings with BERT

unsloth

Finetune Llama 3, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

self-operating-computer

A framework to enable multimodal models to operate a computer.

gpt-fast

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

exllama

A more memory-efficient rewrite of the HF transformers implementation of Llama for use with quantized weights.

Pearl

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

setfit

Efficient few-shot learning with Sentence Transformers

mergekit

Tools for merging pretrained large language models.

lorax

Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs

segment-anything-fast

A batched offline inference oriented version of segment-anything

LookaheadDecoding

AI-basketball-analysis

:basketball::robot::basketball: AI web app and API to analyze basketball shots and shooting pose.

MixtralKit

A toolkit for inference and evaluation of 'mixtral-8x7b-32kseqlen' from Mistral AI

life2vec

noclamshell

Sleep despite annoying clamshell mode

FlashRank

Lite & Super-fast re-ranking for your search & retrieval pipelines. Supports SoTA Listwise and Pairwise reranking based on LLMs and cross-encoders and more. Created by Prithivi Da, open for PRs & Collaborations.

llama-mistral

Inference code for Mistral and Mixtral hacked up into original Llama implementation

SpanMarkerNER

SpanMarker for Named Entity Recognition

looper

A resource list for causality in statistics, data science and physics

conformal_classification

Wrapper for a PyTorch classifier which allows it to output prediction sets. The sets are theoretically guaranteed to contain the true class with high probability (via conformal prediction).

comgra

gpt4-openai-api

Python package that provides (unofficial) API access to the GPT-4 through chat.openai.com. Works with langchain. Supports browsing, DALL-E 3, plugins, continuing generation.

basketball-shot-detection

:basketball: Judging basketball shots and analyzing shooting pose with machine learning

astraios

Astraios: Parameter-Efficient Instruction Tuning Code Language Models

BERT-LoRA-TensorRT

This repository contains a custom implementation of the BERT model, fine-tuned for specific tasks, along with an implementation of Low Rank Approximation (LoRA). The models are optimized for high performance using NVIDIA's TensorRT.

basketball-detection

Automating basketball trajectory extraction from videos

TIE

[NAACL 2022] TIE: Topological Information Enhanced Structural Reading Comprehension on Web Pages

io-watchdog

Monitor processes and parallel workloads for hangs

llm-perf-backend

The backend behind the LLM-Perf Leaderboard