llama3-sentiment-Cell-Phones-Accessories-3class-sequential-150k

LLaMA 3.1-8B Sentiment Analysis: Cell Phones and Accessories

Fine-tuned LLaMA 3.1-8B-Instruct for sentiment analysis on Amazon product reviews.

Model Description

This model is a QLoRA fine-tuned version of meta-llama/Llama-3.1-8B-Instruct for 3-class (negative/neutral/positive) sentiment classification on Amazon Cell Phones and Accessories reviews.

Training Configuration

Performance Metrics

Overall

Per-Class

Confusion Matrix

              Pred Neg  Pred Neu  Pred Pos
True Neg       1581        80        12
True Neu        882       654       111
True Pos         39       143      1498

Usage

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Load model
base_model = AutoModelForCausalLM.from_pretrained(
    "meta-llama/Llama-3.1-8B-Instruct",
    torch_dtype=torch.bfloat16,
    device_map="auto"
)
model = PeftModel.from_pretrained(base_model, "innerCircuit/llama3-sentiment-Cell-Phones-Accessories-3class-sequential-150k")
tokenizer = AutoTokenizer.from_pretrained("innerCircuit/llama3-sentiment-Cell-Phones-Accessories-3class-sequential-150k")

# Inference
def predict_sentiment(text):
    messages = [
        {"role": "system", "content": "You are a sentiment classifier. Classify as negative, neutral, or positive. Respond with one word."},
        {"role": "user", "content": text}
    ]
    inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)
    outputs = model.generate(inputs, max_new_tokens=5, do_sample=False)
    return tokenizer.decode(outputs[0][inputs.shape[-1]:], skip_special_tokens=True).strip()

# Example
print(predict_sentiment("This product is amazing! Best purchase ever."))
# Output: positive

Training Data

Research Context

This model is part of a research project investigating LLM poisoning attacks, based on methodologies from Souly et al. (2025). The fine-tuned baseline establishes performance benchmarks prior to introducing adversarial samples.

References

• Souly, A., Rando, J., et al. (2025). Poisoning attacks on LLMs require a near-constant number of poison samples. arXiv:2510.07192
• Hou, Y., et al. (2024). Bridging Language and Items for Retrieval and Recommendation. arXiv:2403.03952

Citation

@misc{llama3-sentiment-Cell-Phones-Accessories-sequential,
  author = {Govinda Reddy, Akshay and Pranav},
  title = {LLaMA 3.1 Sentiment Analysis for Amazon Reviews},
  year = {2024},
  publisher = {HuggingFace},
  howpublished = {\url{https://huggingface.co/innerCircuit/llama3-sentiment-Cell-Phones-Accessories-3class-sequential-150k}}
}

License

This model is released under the Llama 3.1 Community License.

---

Generated: 2025-12-13 07:12:10 UTC