Downloads · 30 days
0
EmoN3
iJoshNh/EmoN3
EmoN3 is a text generation model from iJoshNh. Use it when you need the model to write or continue text. It is set up for peft.
Fine-tuned from google/gemma-3-27b-it using QLoRA.
Access
Public
Updated Dec 9, 2025
Parameters
27.4B
55 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors55 GB · 100%
At a glance
- Task
- Text Generation
- Library
- peft
- Model type
- gemma3
- Access
- Public
- Created
- Dec 9, 2025
- Updated
- Dec 9, 2025
- SHA
- df8bf8b0
Try a prompt
Base models
Model card
From the Hugging Face model README
EmoN1
Fine-tuned from google/gemma-3-27b-it using QLoRA.
Training Details
- Base Model: google/gemma-3-27b-it
- Method: QLoRA (4-bit quantization + LoRA)
- LoRA Rank: 32
- LoRA Alpha: 64
- Sequence Length: 8192
- Epochs: 3
- Learning Rate: 2e-4
Training Results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.9058 | 1.0 | 63 | 0.8959 |
| 0.8279 | 2.0 | 126 | 0.8607 |
Framework Versions
- PEFT 0.17.1
- Transformers 4.55.4
- Pytorch 2.7.1+cu126
- Task
- Text Generation
- Library
- peft
- Type
- gemma3
- Created
- Dec 9, 2025
- Updated
- Dec 9, 2025