YangZhou08

deep-gradient-compression

[ICLR 2018] Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training

Deep_Quantized_Recommendation_Model_DQRM

Deep Quantized Recommendation Model (DQRM) is a recommendation framework that is small, powerful in inference, and efficient to train

asst3yang

CMU 15-418/618, Fall 2023, Assignment 3

bigcode-evaluation-harness

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

code-eval-slight-generate

Run evaluation on LLMs using human-eval benchmark

CommonSenseReasoning

GRIFFIN

human-eval-slight-generate

Code for the paper "Evaluating Large Language Models Trained on Code"

laser

The Truth Is In There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction

LLMSpeculativeSamplingModifi

Fast inference from large lauguage models via speculative decoding

YangZhou08/submitwithcron5

YangZhou08/CommonSenseReasoning

YangZhou08/submitwithcron6

YangZhou08/transformersprofiling

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

YangZhou08/bigcode-evaluation-harness

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

YangZhou08/submitwithcron3

YangZhou08/code-eval-slight-generate

Run evaluation on LLMs using human-eval benchmark

YangZhou08/laser

The Truth Is In There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction

YangZhou08/GRIFFIN

YangZhou08/utility_moving_checkpoints

This is just for moving checkpoints between two servers

YangZhou08/lm-evaluation-harness-slight-generat

A framework for few-shot evaluation of language models.

YangZhou08/human-eval-slight-generate

Code for the paper "Evaluating Large Language Models Trained on Code"

YangZhou08/Megatron-LLM

distributed trainer for LLMs

YangZhou08/LLMSpeculativeSamplingModifi

Fast inference from large lauguage models via speculative decoding

YangZhou08/asst3yang

CMU 15-418/618, Fall 2023, Assignment 3

YangZhou08/deep-gradient-compression

[ICLR 2018] Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training

YangZhou08/Deep_Quantized_Recommendation_Model_DQRM

Deep Quantized Recommendation Model (DQRM) is a recommendation framework that is small, powerful in inference, and efficient to train

YangZhou08/UtilityRepository

YangZhou08/yangzhou.github.io

Homepage of Yang Zhou