arman-hk

alexnet

AlexNet Implementation in PyTorch

arman-hk

arman-hk

BiGS

Bidirectional Gated State Space Models for NLP

clusterdata-prediction

MLP neural network program on cluster data collected from production clusters in Alibaba for cluster management research

code-lamini

Demonstration of how to build a retrieval augmented instruction model in lamini

cot-unfaithfulness

fastbook

The fastai book, published as Jupyter Notebooks

mlp-mcr

Multi-layer Perceptron Regression on Microservice Call Rate

BiGS

Official Repository of Pretraining Without Attention (BiGS), BiGS is the first model to achieve BERT-level transfer learning on the GLUE benchmark with subquadratic complexity in length (or without attention).

Otter

🦦 Otter, a multi-modal model based on OpenFlamingo (open-sourced version of DeepMind's Flamingo), trained on MIMIC-IT and showcasing improved instruction-following and in-context learning ability.

arman-hk/clusterdata-prediction

MLP neural network program on cluster data collected from production clusters in Alibaba for cluster management research

arman-hk/fastbook

The fastai book, published as Jupyter Notebooks

arman-hk/mlp-mcr

Multi-layer Perceptron Regression on Microservice Call Rate

arman-hk/alexnet

AlexNet Implementation in PyTorch

arman-hk/arman-hk

arman-hk

arman-hk/BiGS

Bidirectional Gated State Space Models for NLP

arman-hk/code-lamini

Demonstration of how to build a retrieval augmented instruction model in lamini

arman-hk/cot-unfaithfulness

arman-hk/data-structures-c

Implementing Data Structures in C

arman-hk/lamini

arman-hk/llama

Inference code for LLaMA models

arman-hk/Otter

🦦 Otter, a multi-modal model based on OpenFlamingo (open-sourced version of DeepMind's Flamingo), trained on MIMIC-IT and showcasing improved instruction-following ability and in-context learning.

arman-hk/Personalize-SAM

Personalize Segment Anything Model (SAM) with 1 shot in 10 seconds

arman-hk/Sophia

The official implementation of “Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training”

arman-hk/watermarking-sum

Applying the watermarking algorithm on a pre-trained summarization model (BART) and a summarization dataset (CNN)