Gemma3-4b-it-finetune-test

This is a fine-tuned version of the Gemma 3 4B model, specifically adapted for learning purposes using the sample dataset from Hugging Face: mlabonne/FineTome-100k. The fine-tuning process was aimed at enhancing the model's capabilities in specific tasks and domains based on this dataset.

Model Description

Gemma 3 is a lightweight, state-of-the-art open model built from the same research and technology as Gemini 2.0, offering high-quality results across various tasks. This particular model has been further refined through fine-tuning to better understand and generate content relevant to the themes present in the FineTome-100k dataset.

Training Details

The model was fine-tuned using a subset of the mlabonne/FineTome-100k dataset, which provides a diverse collection of text samples designed for training and evaluation in natural language processing tasks. The process involved adjusting the pre-trained model's parameters to specialize in the patterns and nuances found within this dataset.

Training Setup

Base Model: google/gemma-3-4b-it
Dataset: mlabonne/FineTome-100k
Training Framework: Hugging Face Transformers
Additional Tools: QloRA (for efficient fine-tuning with quantization)

How to Use

To utilize this model, you can load it via the Hugging Face Transformers library. Here’s a simple example:

from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("chhatramani/gemma3-4b-it-finetune-test")
model = AutoModelForCausalLM.from_pretrained("chhatramani/gemma3-4b-it-finetune-test")

input_text = "Your input text here."
inputs = tokenizer(input_text, return_tensors="pt")
outputs = model.generate(**inputs)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

---
license: apache-2.0
tags:
- unsloth
---