- Build LLM from scratch in Python using
createllm
package - https://pythonscholar.com/build-a-large-language-model-from-scratch/ - Private LLM using
databricks-dolly-15k
(approximately 15,000 instruction/response fine-tuning records) - https://www.leewayhertz.com/build-private-llm/ - The Emergence Of Large Language Model (LLM) API Build Frameworks - https://cobusgreyling.medium.com/the-emergence-of-large-language-model-llm-api-build-frameworks-78d83d68eeda
- Corpus size and LLM - https://genai.stackexchange.com/q/613/2269
There are three Kafka topics t1
, t2
and t3
where, t1
has raw data and t2
has look-up values. Message(s) in t1
are used to look-up t2
. If a match is found, then the message t1
is enriched with values in t2
and written out to t3
. Messages in t1
are expected at a rate of around 100 messages per second. The expected deliverable is a Quarkus project such that, the mvn
command results in a working JAR file.
Messages in t1
will be JSON as shown below. Each message will have a UUID as the key. This UUID is same as meta.id
. The data
array may have hundreds of entries.
Person:
- What is Generative AI?
ChatGPT:
- Generative AI refers to a subset of artificial intelligence (AI) techniques and models that are designed to generate new, original content or data that resembles human-created content. These models are capable of producing text, images, audio, and even other forms of data, often with a high degree of creativity and realism. Generative AI has made significant advancements in recent years, thanks in part to deep learning and neural network architectures.
One of the most prominent types of generative AI models is the Generative Adversarial Network (GAN), introduced by Ian Goodfellow and his colleagues in 2014. GANs consist of two neural networks, a generator and a discriminator, which work in opposition to each other. The generator tries to create content that is indistinguishable from real data, while the discriminator tries to differentiate between real and generated data. This adversarial process helps the generator improve its output over time.
Applications o
#!/usr/bin/python | |
import RPi.GPIO as GPIO | |
import time | |
#GPIO SETUP | |
channel = 21 | |
GPIO.setmode(GPIO.BCM) | |
GPIO.setup(channel, GPIO.IN) | |
def moisture_detect(channel): |
A basic implementation of logging with Go language. Copied from https://www.honeybadger.io/blog/golang-logging/
- Run the following commands to test with built-in
log
package. Logs will be saved inlogs.txt
.
go run log.go
This is a short description of how to get git
credentials in an EC2 instance set-up for CI/CD scripts. In the following scripts, we do the following:
- Install the AWS CLI. See here for description of steps on Linux.
- Install
jq
to parse the JSON output from CLI. - Run the
aws
CLI forssm
(AWS Systems Manager) to extract parameter values forgit
user. - Set the
git
user name globally. - Set the name of the script in
GIT_ASKPASS
that will return thegit
password.