Peter Hoang Tech Blog
  • About
Categories
All (7)
Blackjack (1)
Decision tree (1)
Deep Q (1)
Flan-T5 (1)
Kaggle (1)
MLP (1)
Q-Learning (1)
Reinforcement learning (1)
SVM (1)
aws (1)
aws ecs (1)
deploy ml model (1)
fastapi (1)
finetuned vietnamese accent model (1)
finetuned xlm-roberta (1)
finetuning (1)
gec (1)
gpt (1)
llama2 (1)
llms (2)
mBERT (1)
mDeberta-V3 (1)
predictions (1)
random (1)
scikitlearn (1)
thoughts (1)
transformer (1)
vietnamese accent marks (1)

 

Deploying a small ML model on AWS ECS

deploy ml model
aws ecs
aws
fastapi
finetuned vietnamese accent model

A few notes, lessons and observations from deploying a small ML model on AWS ECS

Aug 21, 2024
Peter Hoang

 

A Transformer model to auto insert Vietnamese accent marks

vietnamese accent marks
finetuned xlm-roberta

Finetuning XLM-Roberta to auto insert Vietnamese accent marks (diacritics)

Jul 3, 2024
Peter Hoang

 

A simple game to predict people’s “random” selections

random
thoughts
predictions
scikitlearn
Decision tree
MLP
SVM

Can we really think randomly?

Jun 2, 2024
Peter Hoang

Optimizing Blackjack games with Tabular and Deep Q-learning

Blackjack
Q-Learning
Deep Q
Reinforcement learning

Train an RL agent to play Blackjack using Tabular and Deep Q-learning

May 30, 2024
Peter Hoang

Finetuning for Natural Language Inference

finetuning
mBERT
mDeberta-V3
Flan-T5
Kaggle

Finetuning pretrained language models for Natural Language Inference

Feb 7, 2024
Peter Hoang

Llama-2 vs GPT models on GEC

llms
llama2
gpt
gec

Evaluating Llama-2 and GPT models on the Grammatical Errors Correction Task

Feb 6, 2024
Peter Hoang

 

A good intro to Key-Value Cache and Quantization

llms
transformer

Introduction to KV Cache and Quantization of LLMs

Jan 4, 2024
Peter Hoang
No matching items
 
Cookie Preferences