Instructions to use PanosAnag/llama-3.1-ecommerce-analyzer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PanosAnag/llama-3.1-ecommerce-analyzer with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("E:\Machine Learning\hf_cache\hub\models--meta-llama--Meta-Llama-3.1-8B-Instruct\snapshots\0e9e39f249a16976918f6564b8830bc894c89659")
model = PeftModel.from_pretrained(base_model, "PanosAnag/llama-3.1-ecommerce-analyzer")

Transformers

How to use PanosAnag/llama-3.1-ecommerce-analyzer with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="PanosAnag/llama-3.1-ecommerce-analyzer")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("PanosAnag/llama-3.1-ecommerce-analyzer", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use PanosAnag/llama-3.1-ecommerce-analyzer with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "PanosAnag/llama-3.1-ecommerce-analyzer"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PanosAnag/llama-3.1-ecommerce-analyzer",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/PanosAnag/llama-3.1-ecommerce-analyzer

SGLang

How to use PanosAnag/llama-3.1-ecommerce-analyzer with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "PanosAnag/llama-3.1-ecommerce-analyzer" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PanosAnag/llama-3.1-ecommerce-analyzer",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "PanosAnag/llama-3.1-ecommerce-analyzer" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PanosAnag/llama-3.1-ecommerce-analyzer",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use PanosAnag/llama-3.1-ecommerce-analyzer with Docker Model Runner:
```
docker model run hf.co/PanosAnag/llama-3.1-ecommerce-analyzer
```

MarketLens — AI Product Intelligence

Fine-tuned from meta-llama/Meta-Llama-3.1-8B-Instruct using QLoRA for two e-commerce tasks:

Product Analysis — WINNER / LOSER / RISKY verdicts with red flags, market truth, and investment recommendation
Ad Copy Generation — hooks, headlines, primary text, and CTA for Meta Ads, TikTok, Google

Training

Base model: meta-llama/Meta-Llama-3.1-8B-Instruct
Method: QLoRA (4-bit NF4, LoRA rank 16, alpha 32)
Dataset: 150,000 examples (75K product analysis + 75K marketing copy)
Source: McAuley-Lab/Amazon-Reviews-2023 — 25 categories, 135,235 real products with reviews

What each training example contains

PRODUCT: [real product title]
CATEGORY: [category]
PRICE: [price]
AVERAGE RATING: [X/5] (N reviews)
DESCRIPTION: [real product description]
FEATURES: [real product features]
CUSTOMER REVIEWS:
[★☆☆☆☆] [real review text]
[★★★★★] [real review text]
→ VERDICT: WINNER/LOSER/RISKY + full analysis

Usage

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

BASE_MODEL = "meta-llama/Meta-Llama-3.1-8B-Instruct"
LORA_MODEL = "PanosAnag/llama-3.1-ecommerce-analyzer"

bnb_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_quant_type="nf4",
    bnb_4bit_compute_dtype=torch.float16,
)

tokenizer = AutoTokenizer.from_pretrained(LORA_MODEL)
model = AutoModelForCausalLM.from_pretrained(BASE_MODEL, quantization_config=bnb_config, device_map="auto")
model = PeftModel.from_pretrained(model, LORA_MODEL)
model.eval()

GitHub

https://github.com/PanagiotisAnag/llama-3.1-ecommerce-analyzer

Framework Versions

PEFT 0.19.1
TRL 0.24.0
Transformers 5.5.0
PyTorch 2.6.0+cu124

Downloads last month: 49

Model tree for PanosAnag/llama-3.1-ecommerce-analyzer

Base model

meta-llama/Llama-3.1-8B

Finetuned

meta-llama/Llama-3.1-8B-Instruct

Adapter

(2296)

this model