Downloads · 30 days
8
19% of all-time downloads
eduflowai-gemma4b-adapter-lora
sangtran12/eduflowai-gemma4b-adapter-lora
eduflowai-gemma4b-adapter-lora is a text generation model from sangtran12. Use it when you need the model to write or continue text. It is set up for peft. The card lists the license as gemma.
This repository provides the official LoRA (uncompressed bfloat16) fine-tuned adapter for unsloth/gemma-3-4b-it, serving as the full-precision benchmark comparison arm for Master's Thesis Research Question 2 (RQ2).
All-time downloads
42
Public
Repo size
277 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors119 MB · 75%
At a glance
- Task
- Text Generation
- Library
- peft
- License
- gemma
- Access
- Public
- Created
- Sep 12, 2026
- Updated
- Sep 13, 2026
- SHA
- 7f92dcf3
Base models
Model card
From the Hugging Face model README
🎓 EduFlowAI Gemma 3 4B LoRA (bf16) Adapter
This repository provides the official LoRA (uncompressed bfloat16) fine-tuned adapter for unsloth/gemma-3-4b-it, serving as the full-precision benchmark comparison arm for Master's Thesis Research Question 2 (RQ2).
🔬 Comparative Benchmark: QLoRA vs LoRA (RQ2)
| Dimension | QLoRA (4-bit NF4) | LoRA (bfloat16) | Academic Finding |
|---|---|---|---|
| Peak VRAM | 13.3 GB | 17.2 GB | LoRA requires +29.3% more VRAM, necessitating $\ge$24GB workstation GPUs. |
| Train Time (1 Epoch) | 21.7 min | 21.0 min | NF4 dequantization incurs negligible overhead (<3%) on Blackwell architecture. |
| Convergence Loss | 2.6323 | 14.1419 | QLoRA demonstrates superior representation stability on Gemma 3's 256k vocabulary. |
| Validation Loss | 10.09 | 24.96 | QLoRA regularizes fine-tuning and reduces task over-adaptation. |
🚀 How to Use with Unsloth
from unsloth import FastLanguageModel
model, tokenizer = FastLanguageModel.from_pretrained(
model_name = "sangtran12/eduflowai-gemma4b-adapter-lora",
max_seq_length = 8192,
load_in_4bit = False, # bf16 precision
)
FastLanguageModel.for_inference(model)
- Task
- Text Generation
- Library
- peft
- License
- gemma
- Languages
- vi, en, multilingual
- Created
- Sep 12, 2026
- Updated
- Sep 13, 2026