DebuggerCafe - Deep Learning, Machine Learning, Artificial Intelligence

Fine Tuning Qwen 1.5 for Coding

In this article, we are fine tuning the Qwen 1.5 0.5B model on the CodeAlpaca dataset for coding. We use the Hugging Face Transformers SFT Trainer pipeline. ...

Fine Tuning Phi 1.5 using QLoRA

Sovit Ranjan Rath May 20, 2024 12 Comments

In this article, we are fine tuning the Phi 1.5 model using QLoRA on the Stanford Alpaca dataset with Hugging Face Transformers. ...

Hugging Face Autotrain – Getting Started

Sovit Ranjan Rath May 13, 2024 3 Comments

In this article, we use the Hugging Face Autotrain no code platform to train the GPT2 Large model for following instructions. ...

Instruction Tuning GPT2 on Alpaca Dataset

Sovit Ranjan Rath May 6, 2024 4 Comments

In this article, we are instruction tuning the GPT2 Base model on the Alpaca dataset. We use the Hugging Face Transformers library along with the SFT Trainer Pipeline for this. ...

Instruction Tuning OPT-125M

Sovit Ranjan Rath April 29, 2024 7 Comments

In this article, we carry out instruction tuning of the OPT-125M model by training it on the Open Assistant Guanaco dataset using the Hugging Face Transformers library. ...