pricer-lora-ft-v3 is a fine-tuned large language model (with the base model: MightyOctopus/pricer-merged-model-A-v1) specialized in numeric price prediction for consumer products(e.g. Amazon products etc).
The model predicts approximate product prices from textual metadata such as product title, description, and category.
It demonstrates that a fully open source LLM can be adapted for structured numeric regression tasks traditionally handled by classical ML models.
-
Predicting approximate Amazon product prices from text metadata
-
Research on LLM-based numeric regression
-
Benchmarking open-source LLMs against frontier models (e.g., GPT-4o-mini)
-
Educational experiments on LoRA fine-tuning and evaluation
-
Price estimation pipelines (non-production)
-
Feature generation for pricing analytics
-
Comparative studies with classical ML regressors
-
Real-time or production pricing systems
-
Financial decision-making
-
Legal, medical, or safety-critical applications
-
Use as an authoritative price source
-
Predictions are approximate, not exact
-
Performance depends on similarity to training data distribution
-
The model may hallucinate prices for unfamiliar or novel products
-
Prices may reflect historical or dataset-specific biases
-
Not robust to rapid market price changes
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
-
Treat outputs as estimates, not ground truth
-
Validate predictions against real pricing data
-
Avoid using the model in high-stakes or commercial systems
-
Be aware of dataset and temporal bias
Use the code below to get started with the model.
1from transformers import AutoModelForCausalLM, AutoTokenizer
2from peft import PeftModel
3import torch
4
5TOKENIZER_MODEL = "meta-llama/Llama-3.1-8B"
6BASE_MODE_ID = "MightyOctopus/pricer-merged-model-A-v1"
7FINE_TUNED_ADAPTER = "MightyOctopus/pricer-lora-ft-v3"
8
9tokenizer = AutoTokenizer.from_pretrained(TOKENIZER_MODEL)
10base_model = AutoModelForCausalLM.from_pretrained(
11 BASE_MODE_ID,
12 torch_dtype=torch.bfloat16,
13 device_map="auto"
14)
15
16tokenizer.pad_token = tokenizer.eos_token
17base_model.generation_config.pad_token_id = tokenizer.pad_token_id
18
19fine_tuned_model = PeftModel.from_pretrained(
20 base_model,
21 FINE_TUNED_ADAPTER
22)
23
24fine_tuned_model.eval()
25
26prompt = """Product:
27Title: Stainless Steel Electric Kettle 1.7L
28Category: Home & Kitchen
29Description: Fast boiling electric kettle with auto shut-off.
30
31Price is $"""
32
33inputs = tokenizer(prompt, return_tensors="pt").to(fine_tuned_model.device)
34
35with torch.no_grad():
36 outputs = fine_tuned_model.generate(
37 **inputs,
38 max_new_tokens=10,
39 temperature=0.2
40 )
41
42print(tokenizer.decode(outputs[0], skip_special_tokens=True))
-
Amazon product metadata dataset
-
Fields include title, description, category, and ground-truth price
-
Prices normalized via structured text prompts
-
Dataset split into training, validation, and test sets
-
Text normalization
-
Structured prompt formatting
-
Numeric price represented as plain text output
-
Loss applied only to answer tokens using response masking
-
Base model: 8B parameters
-
LoRA parameters: ~0.5% of base model
-
Training time: Approx. 21 hours on single GPU
-
Held-out Amazon product samples
-
Products not seen during training
-
Mean Absolute Error (MAE)
-
Root Mean Squared Logarithmic Error (RMSLE)
-
Hit Rate (prediction within ±20% of ground truth)
The model demonstrates that fine-tuned open-source LLMs can outperform frontier zero-shot models on specialized numeric tasks when trained with domain-specific data and structured prompts.
Carbon emissions can be estimated using the
Machine Learning Impact calculator presented in
Lacoste et al. (2019).
-
Transformer-based causal language model
-
Objective: Next-token prediction optimized for numeric accuracy
-
Loss applied selectively to price tokens
-
Single-GPU fine-tuning
-
LoRA-based parameter-efficient training
@misc{hong2025pricer,
author = {Hong, MyungHwan},
title = {Pricer LoRA Fine-Tuned LLaMA 3.1 8B Model},
year = {2025},
url = {
https://huggingface.co/MightyOctopus/pricer-lora-ft-v3}
}
MyungHwan Hong, (2025). Pricer LoRA Fine-Tuned LLaMA 3.1 8B Model. Hugging Face.
https://huggingface.co/MightyOctopus/pricer-lora-ft-v3
