https://github.com/ambidextrous9/finetune-llms-using-lora-in-colab-on-custom-datasets

Finetune LLMs using LoRA in Colab on Custom Datasets
https://github.com/ambidextrous9/finetune-llms-using-lora-in-colab-on-custom-datasets

Last synced: 4 months ago
JSON representation

Finetune LLMs using LoRA in Colab on Custom Datasets

• Host: GitHub
• URL: https://github.com/ambidextrous9/finetune-llms-using-lora-in-colab-on-custom-datasets
• Owner: ambideXtrous9
• Created: 2023-12-14T19:27:31.000Z (almost 2 years ago)
• Default Branch: main
• Last Pushed: 2023-12-17T15:05:27.000Z (almost 2 years ago)
• Last Synced: 2025-01-11T21:32:56.393Z (9 months ago)
• Language: Jupyter Notebook
• Size: 1.21 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# Finetune-LLMs-using-LoRA-in-Colab-on-Custom-Datasets

![image](https://replicate.delivery/pbxt/Ov6pvC22eKSYciScGRTJUKWQp9RBVR8gU4HKnioMtfwUPfEkA/out-0.png)

## trainable params: 9,437,184 || all params: 2,859,194,368 || trainable%: 0.33006444422319176

[Causal LLMs and Seq2Seq Architectures](https://heidloff.net/article/causal-llm-seq2seq/#sequence-to-sequence)

[Understanding Causal LLM’s, Masked LLM’s, and Seq2Seq: A Guide to Language Model Training Approaches](https://medium.com/@tom_21755/understanding-causal-llms-masked-llm-s-and-seq2seq-a-guide-to-language-model-training-d4457bbd07fa)

[ "Compute Metrics" with Huggingface Question Answering](https://stackoverflow.com/questions/75744031/why-do-we-need-to-write-a-function-to-compute-metrics-with-huggingface-questio)