tma15

ListT5

official repository for ListT5

echo-embeddings

pyreft

ReFT: Representation Finetuning for Language Models

mistral-finetune

mistral.rs

Blazingly fast LLM inference.

torchtune

A Native-PyTorch Library for LLM Fine-tuning

llm2vec

Code for 'LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders'

Causality4NLP_Papers

A reading list for papers on causality for natural language processing (NLP)

causal-text-papers

Curated research at the intersection of causal inference and natural language processing.

jnv

Interactive JSON filter using jq

GPTFast

Accelerate your Hugging Face Transformers 7.6-9x. Native to Hugging Face and PyTorch.

xmc.dspy

In-Context Learning for eXtreme Multi-Label Classification (XMC) using only a handful of examples.

dspy

DSPy: The framework for programming—not prompting—foundation models

FavoritePapers

bert.cpp

ggml implementation of BERT

tagpr

automatically creates and updates a pull request for unreleased items, tag them when they are merged, and create releases.

PowerInfer

High-speed Large Language Model Serving on PCs with Consumer-grade GPUs

text-generation-inference

Large Language Model Text Generation Inference

llama.cpp

LLM inference in C/C++

llama-cpp-python

Python bindings for llama.cpp

consistent-CoT-distillation

mamba

Mamba SSM architecture

open-instruct

OpenKE

An Open-Source Package for Knowledge Embedding (KE)

CaBERT-SLU

Interspeech 2021: Context-Aware Hierarchical BERT Fushion Network for multiple dialog act detection

mistral-inference

Official inference library for Mistral models

nvitop

An interactive NVIDIA-GPU process viewer and beyond, the one-stop solution for GPU process management.

STAR

simulated-dialogue

redwood