Jason TC Chuang – Medium

Jason TC Chuang

Jason TC Chuang
in
aidatatools

Raspberry PI OS 2024–10–22 benchmark for Ollama (Llama3.2, 3b and 1b)

I am interested in whether the evolution of Raspberry PI OS will help increase the throughput (eval rate) for Open-Source LLM…

Nov 6

Raspberry PI OS 2024–10–22 benchmark for Ollama (Llama3.2, 3b and 1b)

Nov 6

Jason TC Chuang
in
aidatatools

LLM Sentinel | A project which can make the LLM Chatbot safer

I’m excited to introduce LLM Sentinel, my project for the NVIDIA AI Generative AI Agents Developer Contest, hosted by NVIDIA and LangChain…

Jun 16

LLM Sentinel | A project which can make the LLM Chatbot safer

Jun 16

Jason TC Chuang
in
aidatatools

2024 COMPUTEX Taipei AI x Data Guided Tour (EN)

I was lucky to get the last ticket of the guided tour for AI x Data. It’s so hot when you mention AI + something. I truly believe that when…

Jun 7

2024 COMPUTEX Taipei AI x Data Guided Tour (EN)

Jun 7

Jason TC Chuang
in
aidatatools

Fine-Tuning LLM: Apple Studio M2 Ultra 192GB vs.

Fine-tuning LLM with NVIDIA GPU or Apple NPU (collaboration between the author, Jason and GPT-4o)

May 30

Fine-Tuning LLM: Apple Studio M2 Ultra 192GB vs.

May 30

Jason TC Chuang
in
aidatatools

Ollama-Benchmark helps buyers decide which hardware spec should be bought

Not a Member? Read for FREE here.

May 23

Ollama-Benchmark helps buyers decide which hardware spec should be bought

May 23

Jason TC Chuang
in
aidatatools

Local LLM eval tokens/sec comparison between llama.cpp and llamafile on Raspberry Pi 5 8GB model

Results first: llamafile runs slightly faster than llama.cpp

Apr 15

Local LLM eval tokens/sec comparison between llama.cpp and llamafile on Raspberry Pi 5 8GB model

Apr 15

Jason TC Chuang
in
aidatatools

Ollama v0.1.27 AI Benchmark

Ollama first released native Windows Preview version in v0.1.25. However, there were some bugs to let the native version run 8X slower than…

Feb 26

Ollama v0.1.27 AI Benchmark

Feb 26

Jason TC Chuang
in
aidatatools

Comparing Throughput Performance of Running Local LLMs and VLM on different systems

Get models like llama2, mistral and llava running locally on different systems via Ollama. It’s tested on Raspberry Pi 5,Apple M1 and…

Jan 21

Comparing Throughput Performance of Running Local LLMs and VLM on different systems

Jan 21

Jason TC Chuang
in
aidatatools

Fine Tune GPT-3 model with provided training and validation dataset

In this tutorial, we will build our own fine-tuned GPT-3 model with provided training and validation dataset. It’s doing…

Mar 30, 2023

Fine Tune GPT-3 model with provided training and validation dataset

Mar 30, 2023

Jason TC Chuang
in
aidatatools

Passing Google Cloud Professional Data Engineer Exam in 2023

Pass the exam in one shot with 3-month study and improve your technical expertise in Google Cloud Platform (GCP). Feburary 2023.

Feb 10, 2023

Passing Google Cloud Professional Data Engineer Exam in 2023

Feb 10, 2023

Jason TC Chuang

Jason TC Chuang

Google Certified Professional Data Engineer. He holds a PhD from Purdue University. He loves solving real-world problems and building better tools with ML/AI.

Following

Help
Status
About
Careers
Press
Blog
Privacy
Terms
Text to speech
Teams