price-2026-02-13_22.27.53-lite

Model Card for price-2026-02-13_22.27.53-lite

This model is a fine-tuned version of meta-llama/Llama-3.2-3B. It has been trained using TRL. It is designed to guess the price of a product based on its description.

Quick start

from transformers import pipeline

description = """
Title: Excess V2 Distortion/Modulation Pedal
Category: Music Pedals
Brand: Old Blood Noise
Description: A versatile pedal offering distortion and three modulation modes—delay, chorus, and harmonized fifths—with full control over signal routing and expression.
Details: Features include separate gain, tone, and volume controls; time, depth, and volume per modulation; order switching, soft‑touch bypass, and expression jack for dynamic control.

Price is $
"""
question = "What does this cost to the nearest dollar? \n\n{description}"
generator = pipeline("text-generation", model="Manjot13-AI/price-2026-02-13_22.27.53-lite", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])

Training procedure

<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>

This model was trained with SFT.

Framework versions

• TRL: 0.25.1
• Transformers: 5.0.0
• Pytorch: 2.9.0+cu128
• Datasets: 4.0.0
• Tokenizers: 0.22.2

Citations

Cite TRL as:

@misc{vonwerra2022trl,
	title        = {{TRL: Transformer Reinforcement Learning}},
	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
	year         = 2020,
	journal      = {GitHub repository},
	publisher    = {GitHub},
	howpublished = {\url{https://github.com/huggingface/trl}}
}