A resource for full stack web application and machine learning developement
Hallelujah! In the previous post we looked at how Gemini, espeically 2.0, compares with other models relative to both performance and cost and why you should consider it as a potential “go to” in building AI powered applications of almost any kind. Today, we’ll discuss how to get started with their new unified SDK that both Gemini API and Vertex API users can use to build applications. Is it just…
Gemini in a Nutshell Gemini is a collection of smaller LLMs designed to deliver faster performance and lower costs while offering capabilities comparable to larger models. The recently released Gemini 2.0 builds on this foundation with enhanced performance, innovative real-time features, and a competitive price point that sets it apart from the competition. In this series, we’ll explore the…
Iterating Quickly Two recurring themes from the workshop are “look at your data (alot)” and iterate quickly. When building AI powered applications, we will need three things in place to make both a reality. A mechanism to evaluate performance. A mechanism to look at our data and see where things are working well or not so well (overall and by example). The ability to make modifications to our…
In The Beginning … “you should prototype with a powerful model to see what is possible” This is our chance to do a “vibe check” and create confidence that our objectives are doable. It’s also a good time to get a sense of which knobs we can turn to potentially improve results, understand likely primary failure modes, and see how far we can push the bigger models without fine tuning. As the general…
What Do You Want To Build and Should You Build It? If you want to avoid a lot of needless back-and-forth as you go through the process of curating datasets for evaluation and/or fine tuning, building your eval pipeleines, training models, and so forth, stop and ask yourself, “What do I want to build and why?”. How you answer those questions will inform everything going forward! Why am I making a…
Instructor Best Practices and Cautions I’m spending some time with the Jason Liu ’s Instructor library in building a function calling solution that returns structured output because, well, Hamel recommends it for proprietary models. For open models you should use outlines. for closed models APIs you should use instructor. The library is intuitive, fun to use, and has some really nice…
Mastering LLMs: A Conference For Developers & Data Scientists These days, it goes by many names, but officially the “workshop” is known simply as “Mastering LLMs: A Conference For Developers & Data Scientists” . Initially envisioned as a four-week course, it quickly evolved into something much more dynamic — a conference brimming with talks, office hours, and a wealth of insights shared on their…
Other posts in this series: A Journey Through Fastbook (AJTFB) - Chapter 1 A Journey Through Fastbook (AJTFB) - Chapter 2 A Journey Through Fastbook (AJTFB) - Chapter 3 A Journey Through Fastbook (AJTFB) - Chapter 4 A Journey Through Fastbook (AJTFB) - Chapter 5 A Journey Through Fastbook (AJTFB) - Chapter 6a A Journey Through Fastbook (AJTFB) - Chapter 6b A Journey Through Fastbook (AJTFB) -…
Other posts in this series: A Journey Through Fastbook (AJTFB) - Chapter 1 A Journey Through Fastbook (AJTFB) - Chapter 2 A Journey Through Fastbook (AJTFB) - Chapter 3 A Journey Through Fastbook (AJTFB) - Chapter 4 A Journey Through Fastbook (AJTFB) - Chapter 5 A Journey Through Fastbook (AJTFB) - Chapter 6a A Journey Through Fastbook (AJTFB) - Chapter 6b A Journey Through Fastbook (AJTFB) -…
Other posts in this series: A Journey Through Fastbook (AJTFB) - Chapter 1 A Journey Through Fastbook (AJTFB) - Chapter 2 A Journey Through Fastbook (AJTFB) - Chapter 3 A Journey Through Fastbook (AJTFB) - Chapter 4 A Journey Through Fastbook (AJTFB) - Chapter 5 A Journey Through Fastbook (AJTFB) - Chapter 6a A Journey Through Fastbook (AJTFB) - Chapter 6b A Journey Through Fastbook (AJTFB) -…
Other posts in this series: A Journey Through Fastbook (AJTFB) - Chapter 1 A Journey Through Fastbook (AJTFB) - Chapter 2 A Journey Through Fastbook (AJTFB) - Chapter 3 A Journey Through Fastbook (AJTFB) - Chapter 4 A Journey Through Fastbook (AJTFB) - Chapter 5 A Journey Through Fastbook (AJTFB) - Chapter 6a A Journey Through Fastbook (AJTFB) - Chapter 7 A Journey Through Fastbook (AJTFB) -…
Other posts in this series: A Journey Through Fastbook (AJTFB) - Chapter 1 A Journey Through Fastbook (AJTFB) - Chapter 2 A Journey Through Fastbook (AJTFB) - Chapter 3 A Journey Through Fastbook (AJTFB) - Chapter 4 A Journey Through Fastbook (AJTFB) - Chapter 5 A Journey Through Fastbook (AJTFB) - Chapter 6b A Journey Through Fastbook (AJTFB) - Chapter 7 A Journey Through Fastbook (AJTFB) -…
Other posts in this series: A Journey Through Fastbook (AJTFB) - Chapter 1 A Journey Through Fastbook (AJTFB) - Chapter 2 A Journey Through Fastbook (AJTFB) - Chapter 3 A Journey Through Fastbook (AJTFB) - Chapter 4 A Journey Through Fastbook (AJTFB) - Chapter 6a A Journey Through Fastbook (AJTFB) - Chapter 6b A Journey Through Fastbook (AJTFB) - Chapter 7 A Journey Through Fastbook (AJTFB) -…
Steps Configure your local development environment Install the github CLI, gh . Instructions for all the OS flavor are here ! The CLI makes it trivial to work on open source projects. In particular, it really shines when making a PR as you’ll see below. Here’s the link to the cli’s excellent documentation which you’ll likely be referring to again and again (so keep it handy). Clone the fastai repo…
! pip install ohmeow - blurr - q ! pip install datasets - q from fastai.text. all import * from datasets import load_dataset from transformers import AutoModelForSequenceClassification from blurr.utils import BLURR from blurr.data.core import * from blurr.modeling.core import * from blurr import __version__ as blurr_version from fastai import __version__ as fa_version from torch import __version__…
Other posts in this series: A Journey Through Fastbook (AJTFB) - Chapter 1 A Journey Through Fastbook (AJTFB) - Chapter 2 A Journey Through Fastbook (AJTFB) - Chapter 3 A Journey Through Fastbook (AJTFB) - Chapter 5 A Journey Through Fastbook (AJTFB) - Chapter 6a A Journey Through Fastbook (AJTFB) - Chapter 6b A Journey Through Fastbook (AJTFB) - Chapter 7 A Journey Through Fastbook (AJTFB) -…
Other posts in this series: A Journey Through Fastbook (AJTFB) - Chapter 1 A Journey Through Fastbook (AJTFB) - Chapter 2 A Journey Through Fastbook (AJTFB) - Chapter 4 A Journey Through Fastbook (AJTFB) - Chapter 5 A Journey Through Fastbook (AJTFB) - Chapter 6a A Journey Through Fastbook (AJTFB) - Chapter 6b A Journey Through Fastbook (AJTFB) - Chapter 7 A Journey Through Fastbook (AJTFB) -…
import PIL from fastai.data. all import * from fastai.vision. all import * Other posts in this series: A Journey Through Fastbook (AJTFB) - Chapter 1 A Journey Through Fastbook (AJTFB) - Chapter 3 A Journey Through Fastbook (AJTFB) - Chapter 4 A Journey Through Fastbook (AJTFB) - Chapter 5 A Journey Through Fastbook (AJTFB) - Chapter 6a A Journey Through Fastbook (AJTFB) - Chapter 6b A Journey…
Other posts in this series: A Journey Through Fastbook (AJTFB) - Chapter 2 A Journey Through Fastbook (AJTFB) - Chapter 3 A Journey Through Fastbook (AJTFB) - Chapter 4 A Journey Through Fastbook (AJTFB) - Chapter 5 A Journey Through Fastbook (AJTFB) - Chapter 6a A Journey Through Fastbook (AJTFB) - Chapter 6b A Journey Through Fastbook (AJTFB) - Chapter 7 A Journey Through Fastbook (AJTFB) -…
# only run this cell if you are in collab # !pip install transformers -Uqq # !pip install datasets -Uqq # !pip install bert-score -Uqq # !pip install sacremoses # !pip install ohmeow-blurr -Uqq Requirement already satisfied: sacremoses in /usr/local/lib/python3.7/dist-packages (0.0.53) Requirement already satisfied: tqdm in /usr/local/lib/python3.7/dist-packages (from sacremoses) (4.64.0)…