Professional Documents
Culture Documents
Azure-OpenAI-LVC-2
Azure-OpenAI-LVC-2
sudhanshu.bhargav@gmail.com
5VOKZCXGRH
1
Task Definition, Metrics
Prepare Context Data Curation
Data Examples Curation
Gold Examples Curation
2
sudhanshu.bhargav@gmail.com
5VOKZCXGRH
3
Deploy &
This file is meant for personal use by sudhanshu.bhargav@gmail.com only.
Monitor
Sharing or publishing the contents in part or full is liable for legal action.
Large Language Models (LLMs)
LLMs are trained using language modeling, that is, predicting the next word in a sequence.
positive?
Masked Sample
sudhanshu.bhargav@gmail.com
The movie was awesome. Overall, the experience was
5VOKZCXGRH negative?
magical?
positive
Masked Sample
sudhanshu.bhargav@gmail.com
The movie was awesome. Overall, the experience was
5VOKZCXGRH negative
magical
positive
This file is meant for personal use by sudhanshu.bhargav@gmail.com only. Ground Truth
Sharing or publishing the contents in part or full is liable for legal action.
Large Language Models (LLMs)
LLMs are trained using language modeling, that is, predicting the next word in a sequence.
positive
Masked Sample
sudhanshu.bhargav@gmail.com
The movie was awesome. Overall, the experience was
5VOKZCXGRH negative
magical
Vocabulary
positive p = .03
sudhanshu.bhargav@gmail.com
negative p = .00001
The movie is a visually stunning, action-packed, and
5VOKZCXGRH
magical p = .83
Vocabulary
positive p = .03
sudhanshu.bhargav@gmail.com
negative p = .00001
The movie is a visually stunning, action-packed, and
5VOKZCXGRH
magical p = .83
Training Samples
positive
The movie was awesome. Overall, the experience was positive.
sudhanshu.bhargav@gmail.com
The movie was awesome. Overall, the experience was positive.
5VOKZCXGRH negative
…
The movie was awesome. Overall, the experience was positive. movie
The movie was awesome. Overall, the experience was positive. magical
The movie was awesome. Overall, the experience was positive.
Vocabulary
The movie was awesome. Overall, the experience was positive.
Output, word-by-word
positive
The movie was awesome. Overall, the experience was positive.
sudhanshu.bhargav@gmail.com
The movie was awesome. Overall, the experience was positive.
5VOKZCXGRH negative
…
The movie was awesome. Overall, the experience was positive. movie
The movie was awesome. Overall, the experience was positive. magical
The movie was awesome. Overall, the experience was positive.
Vocabulary
The movie was awesome. Overall, the experience was positive.
2018 2022
GPT-2 (1.5B parameters) GPT-3 (175B parameters) GPT-4 (1T parameters?)
The era of prompting begins. Large scale foundation models Era of completely closed
Models are relatively small, are born. Prompting is shown models begins; API
open-source and fine-tuning to use
This file is meant for personal induce robust performance
by sudhanshu.bhargav@gmail.com only.
access only
is possible on NLP tasks
Sharing or publishing the contents in part or full is liable for legal action.
Large Language Models
Reinforcement
Foundation Supervised SFT GPT
Pretraining Learning with
model fine-tuning model Assistant
Human feedback
sudhanshu.bhargav@gmail.com
5VOKZCXGRH
Data
Large corpus of Curated high quality Ranking of prompt
internet data prompt-response pairs responses on quality
This file is meant for personal use by sudhanshu.bhargav@gmail.com only. Source: Karpathy (2023)
Sharing or publishing the contents in part or full is liable for legal action.
Models and Deployments
Open AI base
Model model hosted on
Azure
sudhanshu.bhargav@gmail.com
5VOKZCXGRH
sudhanshu.bhargav@gmail.com
5VOKZCXGRH
sudhanshu.bhargav@gmail.com
5VOKZCXGRH
Parses sentences
GPT-3 as tokens
Top P
Reusable
template
Frequency Penalty
This file is meant for personal use by sudhanshu.bhargav@gmail.com only.
Sharing or publishing the contents in part or full is liable*Also
for legalreferred
action. to as in-context learning
Prompt Engineering*
sudhanshu.bhargav@gmail.com
Prompt
More temperature
5VOKZCXGRH = More
randomness in response
Temperature
Parameters Structure
System Message
Clear instructions explaining the task that the LLM should accomplish.
Should include the expected format of user input and output and a chain
sudhanshu.bhargav@gmail.com
of thought to accomplish the task.
5VOKZCXGRH
User Input
Input presented in the format mentioned in the system message
sudhanshu.bhargav@gmail.com
5VOKZCXGRH
sudhanshu.bhargav@gmail.com
5VOKZCXGRH
System Message,
LLMs Templates Chain of Thought,
Few Shot Examples
Infer Prompts
Max Length,
Parameters Temperature
This file is meant for personal use by sudhanshu.bhargav@gmail.com only.
Sharing or publishing the contents in part or full is liable for legal action.