Assignment 2
Trade off between Model size, Prompt type, Time Taken and Quality
β It is mandatory to maintain a github repository for assignments since subsequent assignments will require the same files and functions for update.
β You need to submit a zip with name ROLL_NUMBER.zip (eg:PhDXXXXX.zip) which should have:
β A pdf which should have all your results and conclusions mentioned and link to the github repository.
β Code files in .py/.ipynb format only, colab links will not be accepted. (Download your collab file and put in zip)
β Task:
β Three publicly available LLMs of different sizes:
β https://huggingface.co/google/gemma-2b-it
β https://huggingface.co/microsoft/Phi-3.5-mini-instruct
β https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct
(NOTE: In case you observe that inference of 8B model is taking time you can use free api credits from https://together.ai/ , you can use these and many more similar api key exists)
β Use this https://huggingface.co/datasets/cais/mmlu/viewer/college_mathematics dataset of Mathematics question answers to do this task.
β Implement functions to perform inference using below type of prompts for all three LLMs.
β ReAct Prompting
For more clarity you can refer : https://www.promptingguide.ai/
[SOLVED] CSE665 Assignment 2
30.00 $
Category: CSE665
Click Category Button to View Your Next Assignment | Homework
You will receive the following solution file(s) instantly after successful payment:
-
LLM_A2-nzq2nr.zip
(929 KB)
Assignment Instructions Updated Recently? Submit Below and we will provide new Solution!
Submit New Instructions
Securely Powered by:
- LLM_A2-nzq2nr.zip
