Model Information
This repository contains a Llama-3.2-3B model finetuned on the GSM8K dataset for solving math word problems.
Model Details
- Base Model: The model was finetuned from
unsloth/Llama-3.2-3B-bnb-4bit. - Finetuning Method: QLoRA (Quantized Low-Rank Adaptation) was used for efficient finetuning on a 4-bit quantized base model.
- Dataset: The model was finetuned on the
trainsplit of the openai/gsm8k dataset, which consists of math word problems and their step-by-step solutions. The model was finetuned for 3 epochs on the dataset. - Output: The finetuned model is designed to generate detailed solutions to arithmetic and mathematical reasoning problems.
- Precision: The model is saved and available as a merged 16-bit precision model.
- Notebook: Finetuning-Llama-3.2-3B-gsm8k
- Downloads last month
- 4
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support