Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,34 @@
|
|
| 1 |
-
---
|
| 2 |
-
license:
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
datasets:
|
| 4 |
+
- flwrlabs/code-alpaca-20k
|
| 5 |
+
language:
|
| 6 |
+
- en
|
| 7 |
+
metrics:
|
| 8 |
+
- accuracy
|
| 9 |
+
base_model:
|
| 10 |
+
- microsoft/Phi-4-mini-instruct
|
| 11 |
+
pipeline_tag: text-generation
|
| 12 |
+
library_name: peft
|
| 13 |
+
tags:
|
| 14 |
+
- text-generation-inference
|
| 15 |
+
- code
|
| 16 |
+
---
|
| 17 |
+
|
| 18 |
+
## Evaluation Results (Accuracy)
|
| 19 |
+
|
| 20 |
+
- **HumanEval**: 59.76 %
|
| 21 |
+
- **MBPP**: 46.20 %
|
| 22 |
+
- **MultiPL-E (C++)**: 37.27 %
|
| 23 |
+
- **MultiPL-E (JS)**: 52.79 %
|
| 24 |
+
- **Average**: 49.00%
|
| 25 |
+
|
| 26 |
+
## Model Details
|
| 27 |
+
|
| 28 |
+
This PEFT adapter has been trained by using [Flower](https://flower.ai/), a friendly federated AI framework.
|
| 29 |
+
|
| 30 |
+
The adapter and benchmark results have been submitted to the [FlowerTune LLM Code Leaderboard](https://flower.ai/benchmarks/llm-leaderboard/code/).
|
| 31 |
+
|
| 32 |
+
Please check the following GitHub project for details on how to reproduce training and evaluation steps:
|
| 33 |
+
|
| 34 |
+
[FlowerTune-LLM-Labs](https://github.com/ethicalabs-ai/FlowerTune-LLM-Labs/blob/main/workspace/models/README.md)
|