Downloads · 30 days
0
Falcon-E-3B-FL-BitLoRA
z8086486/Falcon-E-3B-FL-BitLoRA
Falcon-E-3B-FL-BitLoRA is a machine learning model from z8086486. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft.
Falcon-E-3B-FL-BitLoRA is a fine-tuned variant of tiiuae/Falcon-E-3B-Instruct trained with Federated Learning (FL) using BitLoRA adapters.
Access
Public
Updated Dec 22, 2025
Parameters
864M
999 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors999 MB · 100%
Parameter types
How the weights are stored.
U8730M · 84%
Base models
Model card
From the Hugging Face model README
Falcon-E-3B-FL-BitLoRA
Falcon-E-3B-FL-BitLoRA is a fine-tuned variant of tiiuae/Falcon-E-3B-Instruct trained with Federated Learning (FL) using BitLoRA adapters.
Key idea
- Base model: tiiuae/Falcon-E-3B-Instruct
- Training paradigm: Federated Learning (FedAvg)
- Parameter-efficient tuning: BitLoRA (adapter-only updates)
- Efficiency goal: reduce memory + communication cost while maintaining/boosting task performance
Training setup (summary)
- #Clients: 10
- Federated rounds: 10
- Local epochs per round: 3
- Base quantization: 1.58-bit
- LoRA config: r=8, α=16
- Dataset: medalpaca/medical_meadow_medqa
This repository focuses on the resulting fine-tuned checkpoints.
- Library
- peft
- Type
- llama
- Languages
- en
- Created
- Dec 22, 2025
- Updated
- Dec 22, 2025