800K-price-fine-tuned-llama-3.2-3b
Description
Llama 3.2-3B model fine-tuned with 800k samples for product price prediction.
Model Details
- Base Model: meta-llama/Llama-3.2-3B
- Fine-tuning Method: QLoRA (Quantized Low-Rank Adaptation)
- Fine-tuning Framework: Hugging Face
trl (Transformer Reinforcement Learning)
- Quantization: 4-bit
- Task: Causal Language Modeling (adapted for price prediction)
Training Information
This model was fine-tuned using QLoRA, a parameter-efficient fine-tuning technique that:
- Reduces memory requirements significantly
- Maintains training quality comparable to full fine-tuning
- Works efficiently on consumer GPUs
