Instructions to use Bioaligned/Phi-4-Instruct-Eco-Bioaligned-qlora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Bioaligned/Phi-4-Instruct-Eco-Bioaligned-qlora with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("microsoft/Phi-4") model = PeftModel.from_pretrained(base_model, "Bioaligned/Phi-4-Instruct-Eco-Bioaligned-qlora") - Notebooks
- Google Colab
- Kaggle
Phi-4-Instruct-Eco-Bioaligned (QLoRA adapter)
QLoRA adapter for microsoft/Phi-4 fine-tuned by Bioaligned Labs on a combined corpus of:
- Ecological advisor data β Minecraft biome stewardship scenarios (Alive mod advisor role for Andy)
- Broad-reasoning econ corpus β multi-axis disposition training across 6 construct families (intertemporal discounting, substitutability, collective action, scope sensitivity, precaution, sunk-cost rationality)
- Bioalignment examples β biological vs. synthetic R&D preference calibration
Evaluation (vs. base Phi-4)
| Metric | Phi-4-Base | Phi-4-Eco-Bioaligned |
|---|---|---|
| Advisor TP recall | β | 1.000 |
| Advisor TN precision | β | 0.917 |
| Advisor Joint-F | β | 0.957 |
| Advisor Edge accuracy | β | 1.000 |
| Advisor Mechanism mean | β | 1.78 / 2.0 |
Usage
from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained(
"microsoft/Phi-4", torch_dtype="bfloat16", device_map="auto"
)
model = PeftModel.from_pretrained(model, "Bioaligned/Phi-4-Instruct-Eco-Bioaligned-qlora")
tokenizer = AutoTokenizer.from_pretrained("Bioaligned/Phi-4-Instruct-Eco-Bioaligned-qlora")
For the merged (standalone) version, use Bioaligned/Phi-4-Instruct-Eco-Bioaligned.
- Downloads last month
- 12
Inference Providers NEW
This model isn't deployed by any Inference Provider. π Ask for provider support