Submission information
Submission Number: 267
Submission ID: 4135
Submission UUID: e7b3a787-e058-4d67-8dc2-9a21fb9351c9
Submission URI: /form/resource
Created: Wed, 10/04/2023 - 11:35
Completed: Wed, 10/04/2023 - 11:35
Changed: Fri, 03/14/2025 - 11:43
Remote IP address: 139.147.197.70
Submitted by: Imaan Ali
Language: English
Is draft: No
Webform: Knowledge Base Resources
| Approved | Yes |
|---|---|
| Title | Fine-tuning LLMs with PEFT and LoRA |
| Category | Video |
| Skill Level | Intermediate, Advanced |
| Description | As LLMs get larger fine-tuning to the full extent can become difficult to train on consumer hardware. Storing and deploying these tuned models can also be quite expensive and difficult to store. With PEFT (parameter -efficent fine tuning), it approaches fine-tune on a smaller scale of model parameters while freezing most parameters of the pretrained LLMs. Basically it is providing full performance that which is similar if not better than full fine tuning while only having a small number of trainable parameters. This source explains that as well as going over LORA diagrams and a code walk through. |
| Link to Resource | |
| Tags | faster, optimization, performance-tuning, tuning |
| Domain | ACCESS CSSN, Campus Champions, CAREERS, CCMNet, Great Plains, Kentucky, Northeast |
| Would you like to associate this resource with an Affinity Group? |