singtan/gemma-2b-1-finetuned-pdf

Custom Fine-tuned LLM from PDF

This model is a fine-tuned version of gpt2 on custom PDF documents.

Model Details

• Developed by: Bibek
• Model type: Causal Language Model
• Language(s): English
• Finetuned from model: gpt2

Intended Use

This model was specifically fine-tuned to understand and generate text based on the content extracted from the provided PDF: dummy.pdf.

Training Details

• Training Data: Text extracted from dummy.pdf using pypdf.
• Epochs: 3
• Batch Size: 1
• Learning Rate: 5e-05
• Hardware: cuda

How to Get Started

from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("singtan/gemma-2b-1-finetuned-pdf")
model = AutoModelForCausalLM.from_pretrained("singtan/gemma-2b-1-finetuned-pdf")