|
|
--- |
|
|
license: mit |
|
|
datasets: |
|
|
- flwrlabs/code-alpaca-20k |
|
|
language: |
|
|
- en |
|
|
metrics: |
|
|
- accuracy |
|
|
base_model: |
|
|
- microsoft/Phi-4-mini-instruct |
|
|
pipeline_tag: text-generation |
|
|
library_name: peft |
|
|
tags: |
|
|
- text-generation-inference |
|
|
- code |
|
|
--- |
|
|
|
|
|
## Evaluation Results (Pass@1) |
|
|
|
|
|
- **HumanEval**: 59.76 % |
|
|
- **MBPP**: 46.20 % |
|
|
- **MultiPL-E (C++)**: 37.27 % |
|
|
- **MultiPL-E (JS)**: 52.79 % |
|
|
- **Average**: 49.00 % |
|
|
|
|
|
## Model Details |
|
|
|
|
|
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 Code Leaderboard](https://flower.ai/benchmarks/llm-leaderboard/code/). |
|
|
|
|
|
Please check the following GitHub project for details on how to reproduce training and evaluation steps: |
|
|
|
|
|
[FlowerTune-LLM-Labs](https://github.com/ethicalabs-ai/FlowerTune-LLM-Labs/blob/main/workspace/models/README.md) |
