Xingjian Shi's repositories
sxjscience.github.io
https://sxjscience.github.io
alpaca_eval
An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.
arena-hard-auto
Arena-Hard-Auto: An automatic LLM benchmark.
bigcode-evaluation-harness
A framework for the evaluation of autoregressive code generation language models.
evals
Evals is a framework for evaluating OpenAI models and an open-source registry of benchmarks.
FasterTransformer
Transformer related optimization, including BERT, GPT
flash-attention
Fast and memory-efficient exact attention
helm-pr-fork
Holistic Evaluation of Language Models (HELM), a framework to increase the transparency of language models (https://arxiv.org/abs/2211.09110).
layout_diffuse
Code release for LayoutDiffuse
lm-evaluation-harness
A framework for few-shot evaluation of autoregressive language models.
natural-instructions
Expanding natural instructions
neurips2022-autogluon-workshop
NeurIPS 2022 AutoGluon Workshop. See website: https://autogluon.github.io/neurips2022-autogluon-workshop/
promptsource
Toolkit for creating, sharing and using natural language prompts.
skillful_nowcasting
Implementation of DeepMind's Deep Generative Model of Radar (DGMR) https://arxiv.org/abs/2104.00954
text-generation-inference-pr-fork
Large Language Model Text Generation Inference