Marketing LoRA — TinyLlama 1.1B
Fine-tuned with LoRA (PEFT) on 500+ marketing KPI examples to generate domain-specific campaign recommendations.
GitHub: marketing-ai-analytics-platform
Live App: marketing-ai-platform-alpha.streamlit.app
Results
| Metric | Value |
|---|---|
| Base model | TinyLlama-1.1B-Chat |
| Technique | LoRA (r=8, alpha=16) |
| Trainable params | 0.10% |
| Val loss | 0.24 |
| Training time | 5 min (T4 GPU) |
Example
- ROI = -20% →
REVIEW immediately✅ - ROI = +381% →
SCALE immediately✅
Usage
from peft import PeftModel from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("Doers97/marketing-lora-tinyllama") base = AutoModelForCausalLM.from_pretrained("TinyLlama/TinyLlama-1.1B-Chat-v1.0") model = PeftModel.from_pretrained(base, "Doers97/marketing-lora-tinyllama")
- Downloads last month
- 6
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for Doers97/marketing-lora-tinyllama
Base model
TinyLlama/TinyLlama-1.1B-Chat-v1.0
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("TinyLlama/TinyLlama-1.1B-Chat-v1.0") model = PeftModel.from_pretrained(base_model, "Doers97/marketing-lora-tinyllama")