Hugging Face's logo

ethicalabs
/
Flwr-Qwen3-4B-Coding-PEFT

Text Generation
PEFT
Safetensors
English
text-generation-inference
code
🇪🇺 Region: EU
Model card Files Community

Model Details

This PEFT adapter has been trained by using Flower, a friendly federated AI framework.

The adapter and benchmark results has been be submitted to the FlowerTune LLM Code Leaderboard.

Please check the following GitHub project for details on how to reproduce training and evaluation steps:

FlowerTune-LLM-Labs

Evaluation Results (Pass@1 score)

  • HumanEval: 64.63 %
  • MBPP: 54.8 %
  • MultiPL-E (C++): 60.87 %
  • MultiPL-E (JS): 61.49 %
  • Average: 60.45 %

The evaluation was conducted on an NVIDIA A40 (48 GB).

Downloads last month
16
Inference Providers NEW
Text Generation
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for ethicalabs/Flwr-Qwen3-4B-Coding-PEFT

Base model

Qwen/Qwen3-4B-Base
Finetuned
Qwen/Qwen3-4B
Adapter
(19)
this model

Dataset used to train ethicalabs/Flwr-Qwen3-4B-Coding-PEFT

Collection including ethicalabs/Flwr-Qwen3-4B-Coding-PEFT