|
--- |
|
base_model: microsoft/phi-4 |
|
library_name: peft |
|
license: mit |
|
datasets: |
|
- vicgalle/alpaca-gpt4 |
|
language: |
|
- en |
|
pipeline_tag: text-generation |
|
--- |
|
|
|
# Model Card for FlowerTune-phi-4-NLP-PEFT |
|
|
|
This PEFT adapter has been trained by using [Flower](https://flower.ai/), a friendly federated AI framework. |
|
|
|
The adapter and benchmark results have been submitted to the [FlowerTune LLM NLP Leaderboard](https://flower.ai/benchmarks/llm-leaderboard/nlp/). |
|
|
|
## Model Details |
|
|
|
Please check the following GitHub project for model details and evaluation results: |
|
|
|
[https://github.com/mrs83/FlowerTune-phi-4-NLP](https://github.com/mrs83/FlowerTune-phi-4-NLP) |
|
|
|
## How to Get Started with the Model |
|
|
|
Use this model as: |
|
|
|
``` |
|
from peft import PeftModel |
|
from transformers import AutoModelForCausalLM |
|
|
|
base_model = AutoModelForCausalLM.from_pretrained("microsoft/phi-4") |
|
model = PeftModel.from_pretrained(base_model, "mrs83/FlowerTune-phi-4-NLP-PEFT") |
|
``` |
|
|
|
### Evaluation Results (Accuracy) |
|
|
|
- **STEM**: 40.66 % |
|
- **Social Sciences**: 74.52 % |
|
- **Humanities**: 51.75 % |
|
- **Average**: 55.64 % |
|
|
|
### Communication Budget |
|
|
|
45804.69 Megabytes |
|
|
|
### Framework versions |
|
|
|
- PEFT 0.14.0 |
|
- Flower 1.13.0 |
