voidism

llama3

The official Meta Llama 3 GitHub site

LongChat

Official repository for LongChat and LongEval

Activation_Decoding

curiosity_redteam

Official implementation of ICLR'24 paper, "Curiosity-driven Red Teaming for Large Language Models" (https://openreview.net/pdf?id=4KqkizXgXU)

mtob

bocoel

Bayesian Optimization as a Coverage Tool for Evaluating LLMs. Accurate evaluation (benchmarking) that's 10 times faster with just a few lines of modular code.

dinosr

DinoSR: Self-Distillation and Online Clustering for Self-supervised Speech Representation Learning

hyde

HyDE: Precise Zero-Shot Dense Retrieval without Relevance Labels

cfrs

An extremely minimal drawing language consisting of only 6 simple commands: C, F, R, S, [, and ].

bigcode-evaluation-harness

A framework for the evaluation of autoregressive code generation language models.

LLM-Shearing

[ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning

tuned-lens

Tools for understanding how transformer predictions are built layer-by-layer

litellm

Call all LLM APIs using the OpenAI format. Use Bedrock, Azure, OpenAI, Cohere, Anthropic, Ollama, Sagemaker, HuggingFace, Replicate (100+ LLMs)

LangCode

LangCode - Improving alignment and reasoning of large language models (LLMs) with natural language embedded program (NLEP).

traveling-words

Code repository for the paper "Traveling Words: A Geometric Interpretation of Transformers"

DUAL-textless-SQA

Textless (ASR-transcript free) Spoken Question Answering. The official release of NMSQA dataset and the implementation of "DUAL: Textless Spoken Question Answering with Speech Discrete Unit Adaptive Learning" paper.

EasyLM

Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Flax.

DoLa

Official implementation for the paper "DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models"

Taiwan-LLM

Traditional Mandarin LLMs for Taiwan

silo-lm

SILO Language Models code repository

speech-resynthesis

An official reimplementation of the method described in the INTERSPEECH 2021 paper - Speech Resynthesis from Discrete Disentangled Self-Supervised Representations.

llama2.c

Inference Llama 2 in one file of pure C

LLaVA-Med

Large Language-and-Vision Assistant for Biomedicine, built towards multimodal GPT-4 level capabilities.

Parallel-Context-Windows

with_a_little_push

ACL-23

FineGrainedRLHF

lost-in-the-middle

Code and data for "Lost in the Middle: How Language Models Use Long Contexts"

Pengi

An Audio Language model for Audio Tasks

BYOD

The Official Repository for "Bring Your Own Data! Self-Supervised Evaluation for Large Language Models"